© 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. 108274
    Prev
    Next
    INDEX
    Explanations

    elements and references related to web development scripts and dependencies

    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
     Blair
    -0.08
     Barcl
    -0.07
     Bout
    -0.07
     fitte
    -0.07
    èįī
    -0.07
     bana
    -0.07
    loit
    -0.06
    åij³
    -0.06
    _simps
    -0.06
    itzer
    -0.06
    POSITIVE LOGITS
     response
    0.08
     Response
    0.08
     respond
    0.08
     Respond
    0.08
    åĵį
    0.08
    respond
    0.07
     responding
    0.07
    igen
    0.07
     répond
    0.07
     Responses
    0.07
    Activations Density 0.001%

    No Known Activations