© 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. 15-LLAMASCOPE-RES-131K
    11. 26774
    Prev
    Next
    INDEX
    Explanations

    references to terms and policies related to user agreements and privacy

    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
    ate
    -0.07
    ice
    -0.07
    erval
    -0.06
    atetime
    -0.06
    ente
    -0.06
    ant
    -0.06
    ation
    -0.06
    icate
    -0.06
    flag
    -0.05
    ank
    -0.05
    POSITIVE LOGITS
    лиÑĤ
    0.07
    esser
    0.07
    baru
    0.07
     crt
    0.07
    ãĤ¤ãĥ³ãĥĪ
    0.07
     &↵
    0.07
     omas
    0.07
     Dalton
    0.07
    OLS
    0.06
     Wid
    0.06
    Activations Density 0.003%

    No Known Activations