© 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. 27197
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or term related to "ward" or "Ward 9"

    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
    ção
    -0.07
    -être
    -0.07
    emia
    -0.07
    zano
    -0.06
    ÏĤ
    -0.06
    etti
    -0.06
    ype
    -0.06
    ordin
    -0.06
    unci
    -0.06
    ister
    -0.06
    POSITIVE LOGITS
    ward
    0.07
    alaxy
    0.07
    иÑĪ
    0.07
    uman
    0.07
    oret
    0.07
    igan
    0.07
    abouts
    0.07
    red
    0.07
    robe
    0.07
    unos
    0.07
    Activations Density 0.030%

    No Known Activations