© 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. 95018
    Prev
    Next
    INDEX
    Explanations

    descriptors related to film characters, particularly strong female leads

    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
    (æ°´
    -0.08
    ainment
    -0.07
    enburg
    -0.07
    ancement
    -0.07
    594
    -0.06
    blr
    -0.06
     tslint
    -0.06
    Uvs
    -0.06
    MLS
    -0.06
    ovel
    -0.06
    POSITIVE LOGITS
     roles
    0.07
     often
    0.07
    ertype
    0.07
     either
    0.07
    often
    0.06
    Whenever
    0.06
    Often
    0.06
    assa
    0.06
    inox
    0.06
     Often
    0.06
    Activations Density 0.016%

    No Known Activations