© 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. 129348
    Prev
    Next
    INDEX
    Explanations

    mentions of flags and related terms

    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
    æ¯
    -0.06
    illo
    -0.06
    Enlarge
    -0.06
    å§Ĩ
    -0.06
    lop
    -0.06
     Pratt
    -0.06
    ayload
    -0.06
    echan
    -0.06
     holds
    -0.05
    anche
    -0.05
    POSITIVE LOGITS
    pson
    0.07
    ugen
    0.07
    Ïĥον
    0.07
    ged
    0.07
    azzi
    0.07
    infeld
    0.07
     DropIndex
    0.07
    sterol
    0.07
    arty
    0.07
     sö
    0.07
    Activations Density 0.021%

    No Known Activations