© 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. 9-LLAMASCOPE-RES-131K
    11. 95613
    Prev
    Next
    INDEX
    Explanations

    occurrences of logging-related terminology in code

    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
    าย
    -0.07
    angu
    -0.07
    üp
    -0.06
    latin
    -0.06
    éĤ
    -0.06
    ishi
    -0.06
    оÑī
    -0.06
    ClassLoader
    -0.06
     Cold
    -0.06
     Bender
    -0.06
    POSITIVE LOGITS
    sez
    0.07
    á»IJ
    0.07
    Anal
    0.07
    rd
    0.07
    itte
    0.07
    ennen
    0.07
    ourcem
    0.06
    bose
    0.06
    ITTE
    0.06
    \Context
    0.06
    Activations Density 0.002%

    No Known Activations