© 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. 69031
    Prev
    Next
    INDEX
    Explanations

    instances of descriptive language and comparisons

    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
    plx
    -0.06
     Princip
    -0.06
     Pip
    -0.06
    siniz
    -0.06
     voksne
    -0.06
    лиз
    -0.06
    ãĥĭãĤ¢
    -0.06
    èµ°
    -0.05
     mænd
    -0.05
    azard
    -0.05
    POSITIVE LOGITS
     applied
    0.09
     aplic
    0.08
     applies
    0.08
    Apply
    0.08
     Apply
    0.08
     apply
    0.08
     describing
    0.08
     Applied
    0.08
     Applies
    0.07
    .apply
    0.07
    Activations Density 0.037%

    No Known Activations