© 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. 63029
    Prev
    Next
    INDEX
    Explanations

    names of specific animal species and their characteristics

    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
    dera
    -0.07
    sap
    -0.07
    ropp
    -0.07
    upal
    -0.07
    antity
    -0.07
    ugas
    -0.07
    gratis
    -0.07
    _HERE
    -0.07
    acades
    -0.06
    ãĤ¤ãĥ«
    -0.06
    POSITIVE LOGITS
    ichel
    0.06
    atform
    0.06
    osomal
    0.06
    kee
    0.06
    ap
    0.06
    ustral
    0.06
     Pocket
    0.06
    OrCreate
    0.06
     Kelley
    0.05
    iband
    0.05
    Activations Density 0.017%

    No Known Activations