© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    headers or indicators in telecommunication-related content

    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
    stitute
    -0.06
    incare
    -0.06
     r
    -0.05
    ummer
    -0.05
    dera
    -0.05
    aghan
    -0.05
    ographer
    -0.05
     magna
    -0.05
     Goth
    -0.05
    attached
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.07
    .dd
    0.07
    Ùİس
    0.07
    chod
    0.07
    ellular
    0.07
    ÙĨساÙĨ
    0.07
    ebi
    0.07
    MimeType
    0.07
    ï¼³
    0.07
    iali
    0.07
    Activations Density 0.007%

    No Known Activations