© 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. 84599
    Prev
    Next
    INDEX
    Explanations

    quantitative information or statistics related to distances, occurrences, and proportions in various contexts

    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
    anik
    -0.07
     [~,
    -0.07
    æģIJ
    -0.07
    inesis
    -0.06
    Ń
    -0.06
    éļª
    -0.06
    nosis
    -0.06
    ãĥ¼ãĥª
    -0.06
    lien
    -0.06
    ensing
    -0.06
    POSITIVE LOGITS
    orate
    0.08
     to
    0.08
    icha
    0.07
    anim
    0.07
    antly
    0.06
    oppins
    0.06
    eldorf
    0.06
    ิà¸Ī
    0.06
    lech
    0.06
    ider
    0.06
    Activations Density 0.034%

    No Known Activations