© 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. 94108
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or continuity in actions or themes

    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
    icken
    -0.06
    angs
    -0.06
    ighton
    -0.06
     Aw
    -0.06
    awl
    -0.06
    assen
    -0.06
    à¹Ģร
    -0.06
    à¥įरत
    -0.06
    hl
    -0.06
     FAG
    -0.06
    POSITIVE LOGITS
    readcr
    0.07
    icolor
    0.07
    aight
    0.07
    aab
    0.06
    ĭ
    0.06
    èįī
    0.06
    tit
    0.06
    BY
    0.06
    locks
    0.06
    -production
    0.06
    Activations Density 0.115%

    No Known Activations