© 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. 9-LLAMASCOPE-RES-131K
    11. 98641
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and equality movements

    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
    uly
    -0.06
    olet
    -0.06
    942
    -0.06
    ula
    -0.06
    oon
    -0.06
    iffer
    -0.06
    brate
    -0.06
     unf
    -0.06
    askets
    -0.05
    elib
    -0.05
    POSITIVE LOGITS
     Äįe
    0.08
    subplot
    0.07
    .CV
    0.07
     è±
    0.07
    _LOGGER
    0.07
     Hava
    0.07
     kariy
    0.07
    chez
    0.07
    .Marker
    0.07
    osos
    0.06
    Activations Density 0.050%

    No Known Activations