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. 22-LLAMASCOPE-RES-131K
    6. 5317
    Prev
    Next
    INDEX
    Explanations

    numerical data and formats related to time, dates, and hours

    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
    antu
    -0.07
    lesh
    -0.07
    омен
    -0.07
    алов
    -0.07
    los
    -0.06
    velle
    -0.06
    лами
    -0.06
    fillable
    -0.06
    yses
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
    00
    0.11
    18
    0.10
    17
    0.10
    16
    0.10
    14
    0.09
    21
    0.09
    08
    0.09
    23
    0.09
    19
    0.09
    22
    0.08
    Activations Density 0.028%

    No Known Activations