© 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. 116592
    Prev
    Next
    INDEX
    Explanations

    occurrences of key events and descriptions related to organizational changes and developments

    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
    INESS
    -0.07
    ILITY
    -0.06
    riba
    -0.06
    á»IJ
    -0.06
     recess
    -0.06
     Autor
    -0.06
    缤
    -0.06
    ilda
    -0.06
    istring
    -0.06
     assort
    -0.06
    POSITIVE LOGITS
    edBy
    0.08
    336
    0.07
    uent
    0.07
    oci
    0.07
    ähr
    0.06
    ipt
    0.06
     itself
    0.06
     Keller
    0.06
    .OR
    0.06
    áš
    0.06
    Activations Density 0.030%

    No Known Activations