© 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. 106706
    Prev
    Next
    INDEX
    Explanations

    sections and subsections in document structures

    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
    undef
    -0.06
     jež
    -0.06
    ì§ĢëıĦ
    -0.06
    ór
    -0.06
    .baidu
    -0.06
     èĭ¥
    -0.06
    or
    -0.06
     _______,
    -0.06
    ç¸
    -0.06
     above
    -0.06
    POSITIVE LOGITS
    awy
    0.08
    fillType
    0.08
    ahlen
    0.07
     forControlEvents
    0.07
    ventus
    0.07
    matchCondition
    0.07
    ystack
    0.07
    styleType
    0.07
    رز
    0.07
    chal
    0.07
    Activations Density 0.024%

    No Known Activations