© 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. 95687
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and numerical data

    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
    loth
    -0.07
    iller
    -0.07
    laus
    -0.07
    á»ij
    -0.06
    osten
    -0.06
    urve
    -0.06
    atter
    -0.06
    ære
    -0.06
    avicon
    -0.06
    ampie
    -0.06
    POSITIVE LOGITS
    strand
    0.07
    .blank
    0.06
     اÙĦÛĮ
    0.06
    REDENTIAL
    0.06
    _draft
    0.06
    backs
    0.06
     ëĸł
    0.06
    ymi
    0.06
    sus
    0.06
     DISCLAIM
    0.06
    Activations Density 0.035%

    No Known Activations