© 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. 91860
    Prev
    Next
    INDEX
    Explanations

    numerical rankings or scores associated with entities

    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
    imd
    -0.08
    ÅĤu
    -0.07
    .Accessible
    -0.07
     misd
    -0.07
    ubat
    -0.07
    ÑĸнÑĮ
    -0.07
    /******/
    -0.07
    SCRI
    -0.07
    NECT
    -0.06
    važ
    -0.06
    POSITIVE LOGITS
     MES
    0.06
    okers
    0.06
     سخ
    0.05
    ued
    0.05
     Ses
    0.05
    })();↵↵
    0.05
    unist
    0.05
    SSERT
    0.05
     frequent
    0.05
     frequency
    0.05
    Activations Density 0.000%

    No Known Activations