© 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. 17-LLAMASCOPE-RES-131K
    11. 56546
    Prev
    Next
    INDEX
    Explanations

    references to events and celebrations

    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
    275
    -0.09
     Severity
    -0.07
    agger
    -0.07
    ãĥĩãĥ«
    -0.07
    fol
    -0.06
    amen
    -0.06
    .persist
    -0.06
    äºĭåĭĻ
    -0.06
    hec
    -0.06
    opr
    -0.06
    POSITIVE LOGITS
    ÃŃrk
    0.08
    \grid
    0.07
    itung
    0.07
    arti
    0.07
     Continued
    0.07
    ckill
    0.07
    ardu
    0.07
    /hash
    0.07
    velt
    0.07
     continued
    0.07
    Activations Density 0.006%

    No Known Activations