© 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. 95557
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the structure of quotes within text

    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
    oproject
    -0.08
    ãĥ¥
    -0.07
    .UnitTesting
    -0.07
    æł·çļĦ
    -0.07
    poÄį
    -0.07
    orris
    -0.07
    Äı
    -0.06
     миÑģ
    -0.06
     ÑģÑĤоÑĢÑĸн
    -0.06
    ãĥ£
    -0.06
    POSITIVE LOGITS
    572
    0.07
    0.06
    602
    0.06
    eland
    0.06
    ortal
    0.06
    ewood
    0.05
     Cause
    0.05
    ooth
    0.05
    adol
    0.05
    oud
    0.05
    Activations Density 0.053%

    No Known Activations