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

    Neuronpedia

    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. 23-LLAMASCOPE-RES-32K
    11. 12096
    Prev
    Next
    INDEX
    Explanations

    subjective opinions and predictions about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .CommandType
    -0.15
    elay
    -0.15
    UIL
    -0.15
    arna
    -0.15
    IMS
    -0.15
     Pear
    -0.14
    angers
    -0.14
    imiter
    -0.14
     innocent
    -0.14
    vil
    -0.14
    POSITIVE LOGITS
     predicting
    0.18
     pencil
    0.17
     handic
    0.17
     penc
    0.17
     predicts
    0.16
    otch
    0.16
     award
    0.16
     expects
    0.16
     progn
    0.16
     peg
    0.15
    Activations Density 0.068%

    No Known Activations