© 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. 69275
    Prev
    Next
    INDEX
    Explanations

    numerical values or identifiers associated with structured data elements

    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
    ibi
    -0.05
    opp
    -0.05
    ooks
    -0.05
    uron
    -0.05
     _
    -0.05
    Retry
    -0.05
    rights
    -0.05
    ore
    -0.05
    ÅĤÄħ
    -0.05
     Lynch
    -0.05
    POSITIVE LOGITS
    erras
    0.08
    Å¡ak
    0.08
     pedig
    0.07
    inou
    0.07
    ï¸
    0.07
    antt
    0.07
    .AppSettings
    0.07
    (æľĪ
    0.07
    wat
    0.07
    soever
    0.07
    Activations Density 0.010%

    No Known Activations