© 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. 31605
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to genetic sequences and errors

    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
    sep
    -0.07
    aspect
    -0.07
    abus
    -0.07
    perf
    -0.06
    uyu
    -0.06
    SEP
    -0.06
     movement
    -0.06
    phylum
    -0.06
     Separator
    -0.06
    sek
    -0.06
    POSITIVE LOGITS
    boro
    0.08
    кÑĢа
    0.07
    CRET
    0.07
    леÑĩ
    0.07
     Tobacco
    0.07
    <tag
    0.07
     tobacco
    0.07
    OCKET
    0.07
     bases
    0.07
     nucle
    0.07
    Activations Density 0.015%

    No Known Activations