© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61452
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance statistics

    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
    erken
    -0.07
    :animated
    -0.07
    олÑĮно
    -0.06
    CONDS
    -0.06
    WSC
    -0.06
    ERSIST
    -0.06
    !--
    -0.06
    uard
    -0.06
    ç¼
    -0.06
     foul
    -0.06
    POSITIVE LOGITS
    ForObject
    0.07
    ogue
    0.06
    imen
    0.06
    osaic
    0.06
    reopen
    0.06
    #region
    0.06
    raud
    0.06
    avez
    0.06
     fires
    0.06
    ctrl
    0.06
    Activations Density 0.001%

    No Known Activations