© 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. 9-LLAMASCOPE-RES-131K
    11. 95346
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and references to mapping or adjusting variables

    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
    anou
    -0.07
    okes
    -0.07
    orian
    -0.07
    ÑģÑĤи
    -0.07
    licer
    -0.07
    orca
    -0.06
    owski
    -0.06
    _DRV
    -0.06
     éģĵ
    -0.06
    noc
    -0.06
    POSITIVE LOGITS
    oppins
    0.07
    984
    0.06
    hcp
    0.06
    269
    0.06
    Bindings
    0.06
    oppers
    0.06
    hic
    0.06
    623
    0.06
    .getM
    0.06
    eny
    0.06
    Activations Density 0.145%

    No Known Activations