© 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. 93287
    Prev
    Next
    INDEX
    Explanations

    phrases indicating user actions related to adding, signing in, or leaving comments

    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
    æīĢ
    -0.06
    æ¿
    -0.06
    cura
    -0.06
     Hamilton
    -0.06
     closure
    -0.06
    èªł
    -0.06
    ãģ¨ãģĵãĤį
    -0.05
     Poison
    -0.05
    erts
    -0.05
     nour
    -0.05
    POSITIVE LOGITS
    efa
    0.08
    åĮ
    0.07
    aiser
    0.07
    Ùĩا
    0.07
    <Expression
    0.07
    Filename
    0.07
    amarin
    0.07
    ÎŃλ
    0.07
    .synthetic
    0.07
    ujet
    0.07
    Activations Density 0.003%

    No Known Activations