© 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. 17-LLAMASCOPE-RES-131K
    11. 29286
    Prev
    Next
    INDEX
    Explanations

    actions related to throwing in sports contexts

    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
     Richards
    -0.07
    ès
    -0.07
     scratch
    -0.06
    lore
    -0.06
    acha
    -0.06
    int
    -0.06
     jumps
    -0.06
    ndef
    -0.06
    anson
    -0.06
    ount
    -0.06
    POSITIVE LOGITS
    icho
    0.07
    Sizer
    0.07
    ezi
    0.07
    æķ¬
    0.06
    erin
    0.06
    ral
    0.06
    ASSES
    0.06
    inker
    0.06
    straight
    0.06
    TOTYPE
    0.06
    Activations Density 0.016%

    No Known Activations