© 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. 77338
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing and data processing

    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
     “
    -0.07
     âĢª
    -0.06
    ÙĪÛĮÛĮ
    -0.06
    ’
    -0.06
     ‘
    -0.06
     phenomen
    -0.06
    ...↵
    -0.06
     annonces
    -0.06
    太éĥİ
    -0.06
     podnikatel
    -0.06
    POSITIVE LOGITS
    itto
    0.09
    úsqueda
    0.09
    $MESS
    0.08
    berapa
    0.08
    swire
    0.08
    itelist
    0.08
    añ
    0.08
    óng
    0.08
    addir
    0.08
    rowsable
    0.08
    Activations Density 0.002%

    No Known Activations