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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88300
    Prev
    Next
    INDEX
    Explanations

    references to football players and related 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
    arel
    -0.07
    ÙĨØ©
    -0.07
    ench
    -0.06
    riel
    -0.06
    atar
    -0.06
    -Ñħ
    -0.06
    tml
    -0.06
    anda
    -0.06
    ÃŃ
    -0.06
    yan
    -0.06
    POSITIVE LOGITS
    ERVER
    0.07
    kü
    0.07
    ¬¬
    0.07
    ymous
    0.07
    -scalable
    0.07
     кÑĥ
    0.07
    sembles
    0.06
    ADDE
    0.06
    omid
    0.06
    otime
    0.06
    Activations Density 0.001%

    No Known Activations