© 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. 116334
    Prev
    Next
    INDEX
    Explanations

    expressions related to reaching or obtaining something

    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
    ضاÙĨ
    -0.08
     Airways
    -0.07
    abouts
    -0.07
    roz
    -0.06
    immel
    -0.06
     Sim
    -0.06
    hoff
    -0.06
    pNet
    -0.06
    anol
    -0.06
    äll
    -0.05
    POSITIVE LOGITS
    vap
    0.07
    ynet
    0.07
    enko
    0.07
    ASF
    0.06
    enso
    0.06
     benefit
    0.06
     Mention
    0.06
    иÑĤÑĭ
    0.06
    ledo
    0.06
    UFFIX
    0.06
    Activations Density 0.041%

    No Known Activations