© 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 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. 126571
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements related to packages and classes

    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
    tu
    -0.07
    รà¸ĵ
    -0.07
    anken
    -0.07
    è¸ı
    -0.07
    ç¸
    -0.07
    ilee
    -0.07
    ãĥ¼ãĥĩ
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    ufen
    -0.06
    fern
    -0.06
    POSITIVE LOGITS
    agers
    0.07
    _tac
    0.06
    ful
    0.06
     ab
    0.06
     rel
    0.06
     Herbert
    0.06
    osaur
    0.06
     thick
    0.06
    _ONCE
    0.06
    eldorf
    0.06
    Activations Density 0.001%

    No Known Activations