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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29882
    Prev
    Next
    INDEX
    Explanations

    instances of the word "walk" or its variations, indicating a focus on movement or travel

    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
    rego
    -0.07
    å¤ĩ
    -0.07
    ilib
    -0.07
    icari
    -0.06
    848
    -0.06
    ilis
    -0.06
    _DL
    -0.06
    ingleton
    -0.06
    isku
    -0.06
    ittal
    -0.06
    POSITIVE LOGITS
     walk
    0.09
    walk
    0.09
     Walk
    0.09
    Walk
    0.09
    .walk
    0.09
     walked
    0.08
     walks
    0.07
    -talk
    0.07
    _walk
    0.07
    owi
    0.07
    Activations Density 0.012%

    No Known Activations