© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    emotional expressions in relation to social 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
    .↵
    -0.13
    ).↵
    -0.10
    .↵↵
    -0.09
    ãĢĤ↵
    -0.09
    ा.↵
    -0.09
    ."↵
    -0.08
    ".↵
    -0.08
    '.↵
    -0.08
    ?↵
    -0.08
    .bunifuFlatButton
    -0.08
    POSITIVE LOGITS
    ”).
    0.08
    ãĢįãĢĤ
    0.08
    ”?
    0.07
    ãĢĤå½ĵ
    0.07
    __).
    0.07
    ”;
    0.07
    ”ãĢĤ
    0.07
    __)
    0.07
    ”.
    0.07
    =”
    0.07
    Activations Density 0.262%

    No Known Activations