© 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. 15-LLAMASCOPE-RES-131K
    11. 86913
    Prev
    Next
    INDEX
    Explanations

    themes surrounding marginalized identities and relationships

    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
    prise
    -0.07
    ubi
    -0.06
    unu
    -0.06
    omu
    -0.06
    obo
    -0.06
    quez
    -0.06
    eza
    -0.06
    omor
    -0.06
    awl
    -0.06
    }elseif
    -0.06
    POSITIVE LOGITS
     frowned
    0.06
    Genre
    0.06
     contamin
    0.06
     considered
    0.06
     pol
    0.06
    hoff
    0.06
    843
    0.06
     thought
    0.06
    )did
    0.06
    _neurons
    0.05
    Activations Density 0.018%

    No Known Activations