© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29666
    Prev
    Next
    INDEX
    Explanations

    punctuation or formatting elements in text

    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
    ivo
    -0.06
    oco
    -0.06
     constitution
    -0.06
     recip
    -0.06
    одаÑĢ
    -0.06
    acam
    -0.06
    apı
    -0.06
    ãĤĥ
    -0.06
     sky
    -0.06
     Harbor
    -0.06
    POSITIVE LOGITS
     Sheridan
    0.07
    eneg
    0.07
    flags
    0.07
    bz
    0.07
     aba
    0.07
    urma
    0.07
    aba
    0.06
    classname
    0.06
    =Value
    0.06
    isch
    0.06
    Activations Density 0.000%

    No Known Activations