© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    references to subjective experiences and evaluations of situations or entities

    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
    uled
    -0.08
    ardless
    -0.08
    ÅĻev
    -0.07
    immel
    -0.07
    orges
    -0.07
    Animating
    -0.07
    .volley
    -0.07
    either
    -0.07
    æĴŃ
    -0.07
    bih
    -0.06
    POSITIVE LOGITS
     may
    0.07
     partly
    0.07
     territory
    0.06
     also
    0.06
     Territory
    0.06
     partially
    0.06
     includes
    0.05
    /part
    0.05
    overlap
    0.05
     include
    0.05
    Activations Density 0.016%

    No Known Activations