© 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. 123242
    Prev
    Next
    INDEX
    Explanations

    identifiers and specifications related to biological entities or sequences

    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
     imm
    -0.06
    виÑĤ
    -0.06
    iani
    -0.05
     bore
    -0.05
     Hab
    -0.05
    amas
    -0.05
     Nurses
    -0.05
     Ma
    -0.05
     The
    -0.05
     sank
    -0.05
    POSITIVE LOGITS
    ellan
    0.08
    eÄį
    0.08
    KHTML
    0.08
    ogue
    0.08
    _DECLS
    0.07
    )((((
    0.07
    -wsj
    0.07
    orado
    0.07
    ãģķãĤī
    0.07
    ISOString
    0.07
    Activations Density 0.054%

    No Known Activations