© 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. 87506
    Prev
    Next
    INDEX
    Explanations

    geometrical properties and measurements related to volume and area

    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
     Operating
    -0.06
     operating
    -0.06
    /rem
    -0.06
     operate
    -0.06
    oper
    -0.06
     rem
    -0.05
     NOM
    -0.05
     ephem
    -0.05
    ünst
    -0.05
    rem
    -0.05
    POSITIVE LOGITS
    éĿ¢ç©į
    0.10
    éĿ¢ç§¯
    0.09
    .area
    0.09
    Area
    0.08
     Area
    0.08
    =size
    0.08
    area
    0.08
    ãİ¡
    0.08
    oser
    0.08
    -area
    0.08
    Activations Density 0.077%

    No Known Activations