© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26935
    Prev
    Next
    INDEX
    Explanations

    references to seriousness or critical undertones in various contexts

    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
    experience
    -0.07
    aklı
    -0.07
    ombo
    -0.07
     é¦Ļ
    -0.07
    /Gate
    -0.07
    çİī
    -0.07
    herits
    -0.07
    jar
    -0.07
    onor
    -0.06
    agged
    -0.06
    POSITIVE LOGITS
    -minded
    0.10
     serious
    0.10
    serious
    0.08
     seriously
    0.08
    lich
    0.08
     minded
    0.07
    ity
    0.07
    istik
    0.07
     seriousness
    0.07
    dehyde
    0.07
    Activations Density 0.014%

    No Known Activations