© 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. 88470
    Prev
    Next
    INDEX
    Explanations

    words related to social situations, feelings of awkwardness, and community engagement 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
    —↵↵
    -0.08
    --↵↵
    -0.08
    --)
    -0.07
    --)↵
    -0.07
    Ĭ¶
    -0.07
    ego
    -0.07
    uzz
    -0.07
    uitka
    -0.07
    raph
    -0.07
    EqualTo
    -0.06
    POSITIVE LOGITS
    ;
    0.08
    :
    0.08
    .
    0.07
    //{{
    0.07
     ;
    0.07
    ØĽ
    0.06
     regarding
    0.06
     :
    0.06
    undef
    0.06
    ),
    0.06
    Activations Density 0.734%

    No Known Activations