© 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. 107691
    Prev
    Next
    INDEX
    Explanations

    sentiments related to betrayal and dishonesty in relationships

    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
    oldt
    -0.07
    ìĦ¸ìļĶ
    -0.07
    inger
    -0.07
    strup
    -0.07
    cot
    -0.07
    ttl
    -0.07
    eof
    -0.07
    паÑĤ
    -0.07
    ãĤ¤ãĥ¤
    -0.07
     migrationBuilder
    -0.07
    POSITIVE LOGITS
     net
    0.07
     Dol
    0.07
     Garrison
    0.07
    ç®Ĺ
    0.06
     ØŃج
    0.06
     del
    0.06
     Dale
    0.06
     Conc
    0.06
     Rah
    0.05
    èĭ±éĽĦ
    0.05
    Activations Density 0.004%

    No Known Activations