© 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. 108733
    Prev
    Next
    INDEX
    Explanations

    instances of directional language and expressions of capability

    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
    elman
    -0.10
     reportedly
    -0.08
    zik
    -0.08
    nown
    -0.08
    quette
    -0.07
    vik
    -0.07
    nsic
    -0.07
    ektor
    -0.07
    iska
    -0.07
    isque
    -0.07
    POSITIVE LOGITS
    aseline
    0.06
     serious
    0.06
     intended
    0.06
    ius
    0.06
    /wp
    0.06
     Casc
    0.06
    ajor
    0.05
    atore
    0.05
     no
    0.05
     bless
    0.05
    Activations Density 0.048%

    No Known Activations