© 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. 76345
    Prev
    Next
    INDEX
    Explanations

    expressions of conflict or disagreement in a social or political context

    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
    ASP
    -0.08
    é
    -0.07
    TOTYPE
    -0.07
    affe
    -0.07
    çīĩ
    -0.07
    ÑijÑĢ
    -0.06
    iná
    -0.06
    POSIT
    -0.06
    ãĢħ
    -0.06
    ooled
    -0.06
    POSITIVE LOGITS
    .Management
    0.07
     recent
    0.07
     management
    0.07
    rof
    0.06
     majority
    0.06
     Management
    0.06
    ItemType
    0.06
     alleged
    0.06
    rots
    0.06
     Elections
    0.06
    Activations Density 0.003%

    No Known Activations