© 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. 60808
    Prev
    Next
    INDEX
    Explanations

    terms related to liability and disclaimers of responsibility

    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
    ambi
    -0.07
    avl
    -0.07
     Spoon
    -0.07
    á»ī
    -0.06
    .Suppress
    -0.06
    eted
    -0.06
    aldi
    -0.06
    à¤ķरण
    -0.06
    ubre
    -0.06
    iffin
    -0.06
    POSITIVE LOGITS
    522
    0.08
    prung
    0.07
    zon
    0.07
    kov
    0.07
    ary
    0.07
    onis
    0.06
    ãĤ¦ãĤ¹
    0.06
    اÙĬت
    0.06
    528
    0.06
     mes
    0.06
    Activations Density 0.003%

    No Known Activations