© 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. 95061
    Prev
    Next
    INDEX
    Explanations

    qualities and characteristics that indicate expertise, talent, or strong personal attributes

    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
    ivec
    -0.08
    biên
    -0.07
    -Identifier
    -0.07
    PRINTF
    -0.07
    elves
    -0.07
    aucoup
    -0.07
     knull
    -0.07
    >');
    -0.07
    GuidId
    -0.07
    .SizeF
    -0.07
    POSITIVE LOGITS
     make
    0.07
     Moo
    0.06
     mi
    0.06
     apt
    0.06
     nature
    0.06
     is
    0.06
     rec
    0.06
    ìŀ¥ìĿĢ
    0.06
    립
    0.06
     dove
    0.06
    Activations Density 0.031%

    No Known Activations