© 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. 5857
    Prev
    Next
    INDEX
    Explanations

    linguistic terminology and concepts related to critique and analysis

    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
    escaping
    -0.06
    éĤ¦
    -0.06
     Balk
    -0.06
     Stanton
    -0.06
    ç§ij
    -0.06
    SPEC
    -0.06
    avo
    -0.06
     Appropri
    -0.06
    STAT
    -0.06
     Kaplan
    -0.06
    POSITIVE LOGITS
     consensus
    0.07
     versions
    0.07
    «a
    0.07
     Version
    0.06
     TNT
    0.06
    /error
    0.06
    variants
    0.06
     Versions
    0.06
     Malone
    0.06
     reading
    0.06
    Activations Density 0.007%

    No Known Activations