© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80732
    Prev
    Next
    INDEX
    Explanations

    terms related to preferences and choices

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    angelo
    -0.07
    ish
    -0.07
    inea
    -0.07
    ãĤ¤ãĤ¯
    -0.07
    urgy
    -0.07
    ê
    -0.07
    suming
    -0.06
    aba
    -0.06
    ned
    -0.06
    romo
    -0.06
    POSITIVE LOGITS
    entially
    0.16
    ential
    0.15
    ably
    0.10
    iable
    0.08
    ensi
    0.08
    encing
    0.08
    renc
    0.07
    ìĤ¬íķŃ
    0.07
     ìĤ¬íķŃ
    0.07
    .Preference
    0.07
    Activations Density 0.010%

    No Known Activations