© 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. 9-LLAMASCOPE-RES-131K
    11. 98965
    Prev
    Next
    INDEX
    Explanations

    comparative statements that express superiority or inferiority

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    insky
    -0.07
    uldu
    -0.07
    linger
    -0.07
    çĴ
    -0.07
    blem
    -0.07
    lemen
    -0.07
    exas
    -0.07
    uits
    -0.07
    .scalablytyped
    -0.06
    oÄį
    -0.06
    POSITIVE LOGITS
    ilor
    0.06
     Viv
    0.06
     anything
    0.06
    à¥įपर
    0.06
    DET
    0.06
     em
    0.06
     Cox
    0.06
    isch
    0.06
     Saunders
    0.05
    693
    0.05
    Activations Density 0.025%

    No Known Activations