© 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. 116358
    Prev
    Next
    INDEX
    Explanations

    references to students and related movements or actions

    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
     Leading
    -0.08
     leading
    -0.08
    leading
    -0.07
    ucht
    -0.07
    Leading
    -0.07
    uchs
    -0.07
    CallBack
    -0.07
     doma
    -0.07
    adt
    -0.07
    ynch
    -0.07
    POSITIVE LOGITS
     away
    0.09
    (move
    0.09
     moved
    0.08
    abel
    0.07
     toward
    0.07
    .move
    0.07
     Away
    0.07
     Dial
    0.07
    移åĪ°
    0.07
     move
    0.07
    Activations Density 0.045%

    No Known Activations