© 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. 63181
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and self-acceptance

    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
    utton
    -0.07
    ernal
    -0.06
     Chess
    -0.06
    [parent
    -0.06
    nof
    -0.06
    &r
    -0.06
    ahren
    -0.06
    ory
    -0.06
    itles
    -0.06
     runs
    -0.06
    POSITIVE LOGITS
    ForMember
    0.06
    ä»ĬæĹ¥
    0.06
    Unc
    0.06
    вай
    0.06
    zo
    0.06
     gag
    0.06
     Dün
    0.06
     privately
    0.06
     chat
    0.06
    ToolTip
    0.06
    Activations Density 0.001%

    No Known Activations