© 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. 5-LLAMASCOPE-RES-131K
    11. 126503
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their characteristics

    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
    alez
    -0.06
    ronym
    -0.06
    acco
    -0.06
    erson
    -0.06
    raci
    -0.06
    ож
    -0.06
    jid
    -0.06
    yw
    -0.06
    Äħż
    -0.06
    ortion
    -0.06
    POSITIVE LOGITS
    iline
    0.07
    ár
    0.07
     EITHER
    0.07
    .RightToLeft
    0.07
    Âłtom
    0.06
    íĴ
    0.06
     ç¸
    0.06
    ingt
    0.06
    oppins
    0.06
    tings
    0.06
    Activations Density 0.008%

    No Known Activations