© 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. 17-LLAMASCOPE-RES-131K
    11. 30379
    Prev
    Next
    INDEX
    Explanations

    punctuation and time markers in historical context

    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
    ucha
    -0.06
    chedulers
    -0.06
    cha
    -0.06
    /ca
    -0.06
     Pending
    -0.06
     Tent
    -0.06
     Recomm
    -0.06
     tents
    -0.06
    pending
    -0.06
    artner
    -0.06
    POSITIVE LOGITS
    PUTE
    0.07
    ños
    0.07
     later
    0.07
    lah
    0.07
    ansion
    0.07
    croft
    0.07
    .bz
    0.06
    during
    0.06
    tiv
    0.06
    -toggler
    0.06
    Activations Density 0.023%

    No Known Activations