© 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. 55191
    Prev
    Next
    INDEX
    Explanations

    structured data representations and formatting

    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
    zos
    -0.07
    alach
    -0.07
    ÑĢеж
    -0.07
    loor
    -0.06
    teri
    -0.06
    /he
    -0.06
    elor
    -0.06
     Frequ
    -0.06
    alli
    -0.06
    quee
    -0.06
    POSITIVE LOGITS
    dit
    0.09
    sat
    0.07
    ãİ
    0.07
    umes
    0.07
    ï½į
    0.07
    loha
    0.06
    رÙĬÙĦ
    0.06
    shal
    0.06
    ÃĹ↵↵
    0.06
    Å¡tÄĽ
    0.06
    Activations Density 0.029%

    No Known Activations