© 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. 17-LLAMASCOPE-RES-131K
    11. 126824
    Prev
    Next
    INDEX
    Explanations

    references to negative emotions or negative qualities affecting individuals

    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
    BITS
    -0.07
    egral
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
    ters
    -0.07
    anie
    -0.07
    enda
    -0.07
    ãģĤãģĤ
    -0.07
    tember
    -0.07
    rey
    -0.07
    odem
    -0.07
    POSITIVE LOGITS
    ujet
    0.07
    âĢį
    0.06
    emble
    0.06
    (sp
    0.06
    aat
    0.06
     Duy
    0.06
    ypse
    0.06
    idden
    0.06
    ovit
    0.06
    <source
    0.06
    Activations Density 0.056%

    No Known Activations