© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72814
    Prev
    Next
    INDEX
    Explanations

    concepts related to power, race, and social dynamics impacting communities and identities

    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
    acades
    -0.08
    andin
    -0.07
    intptr
    -0.07
    erez
    -0.07
    /GPL
    -0.07
     sond
    -0.07
    _rq
    -0.07
    ä¸ī级
    -0.07
    anz
    -0.07
    ische
    -0.07
    POSITIVE LOGITS
     differently
    0.07
    /how
    0.07
     shaped
    0.07
     affect
    0.07
     different
    0.06
     affects
    0.06
    %(
    0.06
     might
    0.06
     various
    0.06
     shaping
    0.06
    Activations Density 0.036%

    No Known Activations