© 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. 62439
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly measurements and data

    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
    zel
    -0.08
    heiro
    -0.07
    _ascii
    -0.07
    ugi
    -0.07
    aul
    -0.07
    ausal
    -0.07
    uli
    -0.07
    ÑĦÑĸ
    -0.07
    reater
    -0.07
    .Areas
    -0.07
    POSITIVE LOGITS
    iá»ģn
    0.07
     actionTypes
    0.06
    Ĺı
    0.06
    STREAM
    0.06
    VP
    0.06
    marshall
    0.06
    elsif
    0.06
    43
    0.06
    ħ
    0.05
    vp
    0.05
    Activations Density 0.001%

    No Known Activations