© 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. 9-LLAMASCOPE-RES-131K
    11. 93990
    Prev
    Next
    INDEX
    Explanations

    references to legal or governmental proceedings

    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
    filt
    -0.06
    ãĤĥ
    -0.06
    ASE
    -0.06
     Conte
    -0.06
    IPH
    -0.06
    аÑĪ
    -0.06
    rese
    -0.06
    baugh
    -0.06
    Balancer
    -0.06
    õi
    -0.06
    POSITIVE LOGITS
    UrlParser
    0.07
    amen
    0.07
    sein
    0.06
     ç¶
    0.06
     noreferrer
    0.06
    olv
    0.06
    foot
    0.06
    AutoSize
    0.06
    yard
    0.06
     Dip
    0.06
    Activations Density 0.006%

    No Known Activations