© 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. 27965
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics

    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
     fisse
    -0.07
    asty
    -0.07
    tember
    -0.06
     strav
    -0.06
    ton
    -0.06
    332
    -0.06
    TON
    -0.06
    clare
    -0.06
    jen
    -0.06
     schö
    -0.06
    POSITIVE LOGITS
     pathMatch
    0.07
    _DECLS
    0.07
    .Forms
    0.07
    atin
    0.07
    iglia
    0.06
     Coch
    0.06
    icensed
    0.06
    elin
    0.06
    enson
    0.06
    ï¸ı
    0.06
    Activations Density 0.005%

    No Known Activations