© 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. 745
    Prev
    Next
    INDEX
    Explanations

    forms of the word "know" or related terms that imply knowledge or recognition

    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
    обÑīе
    -0.07
    ấp
    -0.07
     olab
    -0.07
    ÑģÑĤÑĢи
    -0.06
    dea
    -0.06
    icos
    -0.06
    _compat
    -0.06
    atz
    -0.06
     Decomp
    -0.06
    alars
    -0.06
    POSITIVE LOGITS
    ly
    0.09
    ably
    0.08
    ance
    0.07
    Favorites
    0.07
    edly
    0.06
    /request
    0.06
    905
    0.06
    /cal
    0.06
    liÄį
    0.06
    LY
    0.06
    Activations Density 0.027%

    No Known Activations