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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 96098
    Prev
    Next
    INDEX
    Explanations

    ellipses or punctuation indicating omissions or pauses in 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
    ses
    -0.06
    fer
    -0.06
     Sik
    -0.06
    aro
    -0.06
     occ
    -0.06
    hl
    -0.06
    park
    -0.05
    nen
    -0.05
    236
    -0.05
    инки
    -0.05
    POSITIVE LOGITS
    /Runtime
    0.08
    raci
    0.07
    PRINTF
    0.07
    wick
    0.07
    ấy
    0.06
     ìĿ´ìĸ´
    0.06
    weathermap
    0.06
    uida
    0.06
    :Register
    0.06
    iqué
    0.06
    Activations Density 0.004%

    No Known Activations