© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93455
    Prev
    Next
    INDEX
    Explanations

    programming constructs, specifically referencing or defining elements in code

    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
    vod
    -0.07
    ief
    -0.07
    аÑĢан
    -0.07
    ieg
    -0.07
     Herrera
    -0.07
    ãĤ¯ãĥĪ
    -0.07
     Elis
    -0.07
    AMI
    -0.06
     jenter
    -0.06
    (æľ¨
    -0.06
    POSITIVE LOGITS
    atee
    0.07
    tridge
    0.07
    onus
    0.06
    eson
    0.06
    str
    0.06
    ÑģÑĤи
    0.06
     fra
    0.06
     toe
    0.06
    }'",
    0.06
    çĸĨ
    0.06
    Activations Density 0.098%

    No Known Activations