Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44362
    Prev
    Next
    INDEX
    Explanations

    elements of movement and physical actions in a narrative 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
    леж
    -0.07
     Drive
    -0.06
    Drive
    -0.06
    ottage
    -0.06
    oltip
    -0.06
     Sitting
    -0.06
    ucer
    -0.06
    AMERA
    -0.06
     oyn
    -0.06
    okie
    -0.06
    POSITIVE LOGITS
     jog
    0.10
     stride
    0.10
     trot
    0.10
     strides
    0.10
     quick
    0.09
     walking
    0.09
     tro
    0.09
     jogging
    0.09
     duck
    0.09
     tri
    0.08
    Activations Density 0.037%

    No Known Activations