© 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 EvalsExportsAPI 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. 126576
    Prev
    Next
    INDEX
    Explanations

    programming-related definitions and declarations

    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
    ÃŃme
    -0.07
    owie
    -0.07
    iasi
    -0.07
    lauf
    -0.06
    jis
    -0.06
    113
    -0.06
    rud
    -0.06
    ToFront
    -0.06
    ertz
    -0.06
    ieri
    -0.06
    POSITIVE LOGITS
    ̣
    0.08
    ednou
    0.07
    umatic
    0.06
     ÐĴики
    0.06
    oday
    0.06
    žen
    0.06
    Ìī
    0.06
     Seb
    0.06
    _RESOLUTION
    0.06
    764
    0.06
    Activations Density 0.003%

    No Known Activations