© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 14840
    Prev
    Next
    INDEX
    Explanations

    instances of surprise or unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Balt
    -0.15
    ãĤĨ
    -0.15
    æĺŃ
    -0.14
    olumes
    -0.14
    IDO
    -0.14
    avana
    -0.14
    -cond
    -0.14
    à¥Ĥद
    -0.13
    ób
    -0.13
     arreglo
    -0.13
    POSITIVE LOGITS
     surprise
    0.56
     surprises
    0.54
     Surprise
    0.45
     surpr
    0.37
     surprised
    0.33
     unexpected
    0.31
     surprising
    0.30
     shock
    0.28
     pÅĻekvap
    0.28
     treat
    0.27
    Activations Density 0.091%

    No Known Activations