© 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. 15555
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and interactions in dialogue

    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
    eldorf
    -0.07
    éf
    -0.07
    วร
    -0.07
    oog
    -0.06
    iveau
    -0.06
    plus
    -0.06
    ottage
    -0.06
    bling
    -0.06
    phan
    -0.06
    yum
    -0.06
    POSITIVE LOGITS
    lund
    0.07
     Accord
    0.07
    ikon
    0.06
    ãĥ¼ãĥĭ
    0.06
    Tek
    0.06
    shaw
    0.06
    ¯¯¯¯
    0.06
    bron
    0.06
    ÑģоÑĢ
    0.06
    infeld
    0.06
    Activations Density 0.021%

    No Known Activations