© 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. 31509
    Prev
    Next
    INDEX
    Explanations

    statements and dialogue related to personal experiences and admissions

    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
    ázev
    -0.07
    .jasper
    -0.06
     Kemp
    -0.06
    chyb
    -0.06
    427
    -0.06
    .sharedInstance
    -0.06
    uters
    -0.06
    sted
    -0.06
    _terminal
    -0.06
     khúc
    -0.06
    POSITIVE LOGITS
     further
    0.16
     weiter
    0.13
     weitere
    0.13
    è¿Ľä¸ĢæŃ¥
    0.12
     continued
    0.12
     continues
    0.11
     continue
    0.11
    ãģķãĤīãģ«
    0.11
     Further
    0.10
     another
    0.10
    Activations Density 0.016%

    No Known Activations