© 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. 95408
    Prev
    Next
    INDEX
    Explanations

    instructions and methods regarding teaching and behavioral skills

    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
    anka
    -0.07
    ignet
    -0.07
    айд
    -0.07
    lush
    -0.07
    าà¸ĩ
    -0.07
    ynes
    -0.06
    ersh
    -0.06
    els
    -0.06
    pend
    -0.06
    icle
    -0.06
    POSITIVE LOGITS
    屬
    0.07
    elik
    0.07
     drawn
    0.06
    FromClass
    0.06
    Unchecked
    0.06
    cház
    0.06
    untas
    0.06
    ulis
    0.06
     Charity
    0.06
     Pare
    0.06
    Activations Density 0.010%

    No Known Activations