© 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. 69951
    Prev
    Next
    INDEX
    Explanations

    references to educational materials or resources

    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
     tup
    -0.07
    ISCO
    -0.06
    stro
    -0.06
    sworth
    -0.06
    CustomAttributes
    -0.06
    988
    -0.06
    zimmer
    -0.05
    lectual
    -0.05
    leh
    -0.05
     gift
    -0.05
    POSITIVE LOGITS
    ÑĪев
    0.08
     drill
    0.08
    andel
    0.07
     drills
    0.07
     acompan
    0.07
     Bite
    0.07
    .Features
    0.07
    ety
    0.07
     Drill
    0.07
    _geometry
    0.07
    Activations Density 0.003%

    No Known Activations