© 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. 81934
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and their content

    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
    anje
    -0.07
    arro
    -0.06
    moth
    -0.06
    elsen
    -0.06
    viÄį
    -0.06
    vre
    -0.06
    agues
    -0.06
    achi
    -0.06
    rades
    -0.06
    word
    -0.06
    POSITIVE LOGITS
    _proto
    0.06
    ian
    0.06
    iry
    0.06
    =edge
    0.06
     obra
    0.06
    oko
    0.06
     esp
    0.06
    .bridge
    0.06
    ematic
    0.06
    ppard
    0.06
    Activations Density 0.000%

    No Known Activations