© 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. 40560
    Prev
    Next
    INDEX
    Explanations

    references to computer hardware and specifications

    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
    ãģĭ
    -0.06
    òng
    -0.06
    kees
    -0.06
    .AutoSizeMode
    -0.06
     çIJĨ
    -0.06
    rob
    -0.06
    lech
    -0.06
    chip
    -0.06
    cec
    -0.06
    jo
    -0.06
    POSITIVE LOGITS
     etc
    0.08
    ":[{↵
    0.07
     Hlav
    0.07
    \<^
    0.06
     MethodInfo
    0.06
    Compat
    0.06
     Luna
    0.06
    -hot
    0.06
    èº
    0.06
    oại
    0.06
    Activations Density 0.004%

    No Known Activations