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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62870
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functions for managing data and transactions

    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
    aland
    -0.08
    çĿĽ
    -0.07
    пÑĢав
    -0.07
    icari
    -0.07
    å®ļ
    -0.07
     oppos
    -0.07
    azu
    -0.07
    aber
    -0.07
    esz
    -0.07
    ализи
    -0.06
    POSITIVE LOGITS
    arg
    0.07
    auc
    0.07
     substance
    0.06
    รà¸ģ
    0.06
    hint
    0.06
    gin
    0.06
     arg
    0.06
     Kang
    0.06
    ",-
    0.06
     second
    0.06
    Activations Density 0.001%

    No Known Activations