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. 5417
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to sports performance

    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
    못
    -0.06
     Mend
    -0.06
    ieri
    -0.06
    referer
    -0.06
    icz
    -0.06
    ìĹ
    -0.06
    iec
    -0.05
    extr
    -0.05
    uch
    -0.05
     midnight
    -0.05
    POSITIVE LOGITS
     double
    0.10
    double
    0.08
     Double
    0.08
    Double
    0.08
     DOUBLE
    0.07
     CONTRIBUTORS
    0.07
    cheon
    0.07
     twenties
    0.07
    ampo
    0.07
    ouble
    0.07
    Activations Density 0.005%

    No Known Activations