Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96246
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and components

    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
     Berger
    -0.07
     trùng
    -0.06
    orex
    -0.06
    ÑĢоÑģÑĤ
    -0.06
    ÑĢел
    -0.06
    алÑĭ
    -0.06
     Shel
    -0.06
    ASSERT
    -0.06
    -for
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
    loquent
    0.06
    apy
    0.06
    amma
    0.06
     Charleston
    0.06
     Readonly
    0.06
    ored
    0.06
    etsy
    0.06
    iple
    0.06
    ament
    0.06
    .cloudflare
    0.06
    Activations Density 0.011%

    No Known Activations