© 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. 15837
    Prev
    Next
    INDEX
    Explanations

    programming language elements or structures

    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
    ÑĢоÑĩ
    -0.06
    /antlr
    -0.06
     fur
    -0.06
    afari
    -0.06
    porto
    -0.06
    indow
    -0.06
    artment
    -0.06
    Archive
    -0.06
    oteric
    -0.05
    legg
    -0.05
    POSITIVE LOGITS
    ovsky
    0.08
    CharCode
    0.07
    polator
    0.07
    sher
    0.06
    _defs
    0.06
    anker
    0.06
    ialis
    0.06
    .mx
    0.06
    Âłtom
    0.06
    æĤ
    0.06
    Activations Density 0.000%

    No Known Activations