© 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. 76188
    Prev
    Next
    INDEX
    Explanations

    terms related to limitations and restrictions

    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
    ÑĢав
    -0.07
    lip
    -0.06
    ẹn
    -0.06
     (~(
    -0.06
    opolitan
    -0.06
    ultipart
    -0.06
    orta
    -0.06
    аÑĢод
    -0.06
    rbrace
    -0.06
    วล
    -0.06
    POSITIVE LOGITS
    upo
    0.07
    yles
    0.06
     ext
    0.06
     khúc
    0.06
    strup
    0.06
     Tout
    0.06
     bá»ķ
    0.06
    ASCII
    0.06
    ehir
    0.06
    atest
    0.06
    Activations Density 0.001%

    No Known Activations