© 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. 116795
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "all" and its relationship to various nouns

    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
    pt
    -0.06
     Trev
    -0.06
    _PT
    -0.05
    329
    -0.05
    ryption
    -0.05
    æŁĦ
    -0.05
     bail
    -0.05
    _CM
    -0.05
    alis
    -0.05
    [out
    -0.05
    POSITIVE LOGITS
    ColumnInfo
    0.08
     details
    0.08
    details
    0.08
    ç»Ĩ
    0.07
    .latest
    0.07
     Äijầy
    0.07
    nde
    0.07
    latest
    0.07
    /latest
    0.07
    Ñĥнк
    0.07
    Activations Density 0.013%

    No Known Activations