© 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. 89725
    Prev
    Next
    INDEX
    Explanations

    phrases that express readiness or intention to take action

    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
    Ñģам
    -0.07
    omy
    -0.07
    (EFFECT
    -0.07
     handjob
    -0.07
    вод
    -0.07
    utz
    -0.07
    din
    -0.07
    ented
    -0.07
    ulton
    -0.07
    .fhir
    -0.07
    POSITIVE LOGITS
     ready
    0.09
     challenge
    0.07
     action
    0.06
     bid
    0.06
    lif
    0.06
     Ready
    0.06
    readcr
    0.06
     tackle
    0.06
    ready
    0.06
     RECEIVER
    0.06
    Activations Density 0.018%

    No Known Activations