© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56365
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly days and seasons

    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
    âĢ¦↵
    -0.06
     pr
    -0.06
     od
    -0.06
    iss
    -0.06
    imir
    -0.06
     midnight
    -0.06
    icker
    -0.06
    å®ĺ
    -0.05
    ÑĮ
    -0.05
    aday
    -0.05
    POSITIVE LOGITS
    llib
    0.07
    nest
    0.07
    iversit
    0.07
    _TRA
    0.07
    imson
    0.07
    errer
    0.07
    porno
    0.07
    nist
    0.07
    viz
    0.07
    WithData
    0.07
    Activations Density 0.038%

    No Known Activations