© 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. 128593
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the quality and reliability of systems or data

    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
     zwar
    -0.08
    ché
    -0.07
    astes
    -0.07
    /mit
    -0.07
     wherever
    -0.07
    리ìĹIJ
    -0.07
    -nil
    -0.07
    /=
    -0.07
    isque
    -0.07
    chein
    -0.07
    POSITIVE LOGITS
     anymore
    0.12
     nor
    0.12
     or
    0.11
     nÃło
    0.11
     anything
    0.09
     either
    0.09
    -либо
    0.09
     oder
    0.09
     Nor
    0.08
     EITHER
    0.08
    Activations Density 0.062%

    No Known Activations