© 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. 81988
    Prev
    Next
    INDEX
    Explanations

    details about hairstyles and hair accessories

    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
    cki
    -0.07
     Flam
    -0.07
     Settlement
    -0.06
     repr
    -0.06
    ıma
    -0.06
    ãng
    -0.06
    бав
    -0.06
    éĶ®
    -0.06
    ÏĦζ
    -0.06
     deletion
    -0.06
    POSITIVE LOGITS
     scalp
    0.08
    aben
    0.06
     Girls
    0.06
     ear
    0.06
     Pony
    0.06
    odos
    0.06
     Pine
    0.06
     Knot
    0.06
     PLL
    0.06
     conce
    0.06
    Activations Density 0.003%

    No Known Activations