© 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. 60614
    Prev
    Next
    INDEX
    Explanations

    expressions of personal sentiment or perspectives on societal issues

    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
    sic
    -0.07
     (`
    -0.07
    721
    -0.06
     `
    -0.06
    sen
    -0.06
    /how
    -0.06
     "...
    -0.06
     “âĢ¦
    -0.06
    íļį
    -0.06
    ÙIJ
    -0.06
    POSITIVE LOGITS
    asje
    0.08
    adol
    0.07
    arro
    0.07
    vou
    0.07
    atem
    0.07
    anske
    0.07
    iani
    0.06
    &gt
    0.06
    aison
    0.06
    iggers
    0.06
    Activations Density 0.001%

    No Known Activations