© 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. 39367
    Prev
    Next
    INDEX
    Explanations

    conversational exchanges and emotional expressions related to personal experiences

    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
    arth
    -0.06
    kers
    -0.06
    imers
    -0.06
    ŀæĢ§
    -0.06
    475
    -0.06
    EV
    -0.06
    tics
    -0.06
    /gin
    -0.06
    ă
    -0.06
    enge
    -0.05
    POSITIVE LOGITS
    енÑĮ
    0.07
    ниÑĤелÑĮ
    0.06
     ifndef
    0.06
    _sibling
    0.06
    ¸
    0.06
    elib
    0.06
    ipse
    0.06
    декÑģ
    0.06
    alloca
    0.06
    odia
    0.06
    Activations Density 0.000%

    No Known Activations