© 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. 61783
    Prev
    Next
    INDEX
    Explanations

    code related to data handling and processing functions

    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
     Clarkson
    -0.07
    глÑı
    -0.07
    inheritdoc
    -0.07
    ŀ
    -0.07
    /download
    -0.07
    ewire
    -0.07
    borough
    -0.07
    olle
    -0.06
    unk
    -0.06
    .synthetic
    -0.06
    POSITIVE LOGITS
    .parse
    0.07
    fromJson
    0.07
     parse
    0.07
     Deserialize
    0.07
    _Parse
    0.07
     decoded
    0.07
    decoded
    0.07
    ITS
    0.07
     unserialize
    0.06
    ello
    0.06
    Activations Density 0.008%

    No Known Activations