© 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. 125991
    Prev
    Next
    INDEX
    Explanations

    references to distinct groups or categories

    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
    jni
    -0.07
    urr
    -0.06
    enan
    -0.06
     Bol
    -0.06
     verv
    -0.06
    strup
    -0.06
    uthor
    -0.06
    ванов
    -0.06
    }elseif
    -0.06
    spa
    -0.06
    POSITIVE LOGITS
     different
    0.10
     differently
    0.09
    different
    0.08
    ä¸įåIJĮçļĦ
    0.08
     unique
    0.08
     diferentes
    0.08
    teil
    0.07
    afa
    0.07
    Different
    0.07
    each
    0.07
    Activations Density 0.013%

    No Known Activations