© 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. 9-LLAMASCOPE-RES-131K
    11. 98027
    Prev
    Next
    INDEX
    Explanations

    negative descriptors referring to unattractive or unappealing aspects

    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
    ucci
    -0.08
    able
    -0.07
    fty
    -0.07
    vr
    -0.06
    igo
    -0.06
    pt
    -0.06
    ï¸ı
    -0.06
    /watch
    -0.06
    cing
    -0.06
     Blessed
    -0.06
    POSITIVE LOGITS
    icontrol
    0.07
     enough
    0.07
     unk
    0.07
    -toggler
    0.07
    iteral
    0.07
    جة
    0.07
    ÏĦεÏģ
    0.07
    tility
    0.07
    .utf
    0.07
    stein
    0.07
    Activations Density 0.006%

    No Known Activations