© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86861
    Prev
    Next
    INDEX
    Explanations

    phrases that express searching or looking for something

    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
    опÑĢи
    -0.09
    avigator
    -0.07
    ÅĻich
    -0.07
    ÏĦοκ
    -0.07
    æĹ
    -0.07
    LastError
    -0.07
    enic
    -0.07
    jeme
    -0.07
    estroy
    -0.07
    ëĬ¥
    -0.07
    POSITIVE LOGITS
     look
    0.09
     Look
    0.08
    look
    0.07
     search
    0.07
     elsewhere
    0.07
     looked
    0.07
     seek
    0.07
     looking
    0.07
    _look
    0.06
    Look
    0.06
    Activations Density 0.026%

    No Known Activations