© 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. 17-LLAMASCOPE-RES-131K
    11. 75029
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically percentages and amounts related to classifications and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    519
    -0.06
    lob
    -0.06
    #/
    -0.06
    lineno
    -0.06
    avors
    -0.06
    .AutoScaleMode
    -0.06
    thon
    -0.06
    ãĥĨãĥ«
    -0.06
    ersiz
    -0.06
    437
    -0.06
    POSITIVE LOGITS
    ister
    0.06
     extrad
    0.06
    736
    0.06
    iola
    0.06
    izard
    0.06
    agus
    0.06
    bos
    0.06
    ISTER
    0.06
    /topics
    0.06
    angi
    0.06
    Activations Density 0.018%

    No Known Activations