© 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. 9-LLAMASCOPE-RES-131K
    11. 97215
    Prev
    Next
    INDEX
    Explanations

    code elements related to image selection and UI control in programming

    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
    .kr
    -0.08
    ars
    -0.07
     NavParams
    -0.06
    æ£ļ
    -0.06
    _argument
    -0.06
    ventus
    -0.06
     δε
    -0.06
    ä»Ĭå¹´
    -0.06
    isko
    -0.06
     modne
    -0.06
    POSITIVE LOGITS
     Schro
    0.07
    unning
    0.07
    stone
    0.06
    ippo
    0.06
    _planes
    0.06
    chema
    0.06
    prise
    0.06
    aired
    0.06
     ÙĪÛĮÚ©ÛĮ
    0.06
    bum
    0.06
    Activations Density 0.033%

    No Known Activations