© 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. 78673
    Prev
    Next
    INDEX
    Explanations

    non-textual or formatting elements in the document, such as punctuation marks and symbols

    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
    елиÑĩ
    -0.07
    ayment
    -0.06
    ature
    -0.06
    amate
    -0.06
    redicate
    -0.06
    å§ij
    -0.06
     пÑĢиклад
    -0.06
    usive
    -0.06
    èº
    -0.06
    onso
    -0.06
    POSITIVE LOGITS
    ÃĸL
    0.07
    ãĤ¡
    0.06
     hi
    0.06
     Bonds
    0.06
     Bond
    0.06
     bonds
    0.06
     ног
    0.06
     downstream
    0.06
    mdir
    0.06
    θεÏģ
    0.06
    Activations Density 0.013%

    No Known Activations