© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1375
    Prev
    Next
    INDEX
    Explanations

    terms related to walking and pedestrian activities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    chan
    -0.08
    lef
    -0.08
    agli
    -0.07
    zzle
    -0.07
    гл
    -0.07
    rego
    -0.07
    yen
    -0.07
    pio
    -0.07
    yth
    -0.07
    cks
    -0.07
    POSITIVE LOGITS
    .walk
    0.08
    walking
    0.08
    tober
    0.08
    athon
    0.08
    abouts
    0.07
     walk
    0.07
     stroll
    0.07
    ãĤĥ
    0.07
    about
    0.07
    /run
    0.07
    Activations Density 0.021%

    No Known Activations