© 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. 108885
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or potential

    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
    earn
    -0.07
    zw
    -0.06
    elage
    -0.06
    irie
    -0.06
    маÑĤи
    -0.06
    ometr
    -0.06
    rique
    -0.06
    enberg
    -0.06
    ISCO
    -0.06
    essor
    -0.06
    POSITIVE LOGITS
     trace
    0.08
    ηγ
    0.07
    á»Ĩ
    0.07
    .typ
    0.07
     Trace
    0.06
     seen
    0.06
    ëį°ìĿ´íĬ¸
    0.06
    -tip
    0.06
    (Parcel
    0.06
    trace
    0.06
    Activations Density 0.026%

    No Known Activations