© 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. 76759
    Prev
    Next
    INDEX
    Explanations

    terms related to damage or faults in objects or systems

    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
    opsis
    -0.06
    finity
    -0.06
    merce
    -0.06
    dz
    -0.06
    usto
    -0.06
    oss
    -0.06
    amo
    -0.06
    AsStream
    -0.06
    ós
    -0.06
    grass
    -0.06
    POSITIVE LOGITS
     ones
    0.09
     or
    0.09
    /problem
    0.09
     или
    0.08
    .utility
    0.07
    /loose
    0.07
    ẩu
    0.07
    æĪĸèĢħ
    0.07
    ones
    0.07
     areas
    0.07
    Activations Density 0.021%

    No Known Activations