© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3809
    Prev
    Next
    INDEX
    Explanations

    information related to artwork and its details

    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
    ault
    -0.06
     cust
    -0.06
    Į¨
    -0.06
    ATIC
    -0.06
     curt
    -0.06
    prec
    -0.06
    ogg
    -0.06
    cie
    -0.05
    yp
    -0.05
     Index
    -0.05
    POSITIVE LOGITS
    Signature
    0.08
    signature
    0.08
     Signature
    0.08
    abbo
    0.07
     signature
    0.07
     Leban
    0.07
     imz
    0.07
    .signature
    0.07
    icontrol
    0.07
    ceipt
    0.07
    Activations Density 0.003%

    No Known Activations