© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 28561
    Prev
    Next
    INDEX
    Explanations

    elements of predictability and surprises in storytelling or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing anticipation, unpredictability, or keeping things interesting and uncertain.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bil
    -0.15
    rod
    -0.14
    lou
    -0.14
    oney
    -0.14
    ().'/
    -0.13
     çĦ
    -0.13
    imming
    -0.13
    jal
    -0.13
    ut
    -0.13
    езда
    -0.13
    POSITIVE LOGITS
     surprise
    0.23
     mystery
    0.21
     surprises
    0.20
     Surprise
    0.19
     discovery
    0.19
     mysteries
    0.18
    hid
    0.17
    ystery
    0.17
    Challenge
    0.17
     exciting
    0.16
    Activations Density 0.223%

    No Known Activations