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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 62172
    Prev
    Next
    INDEX
    Explanations

    phrases related to drafting decisions in sports

    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
    eyle
    -0.07
    ħn
    -0.07
    ÑĤоÑİ
    -0.07
    stÃŃ
    -0.07
    agus
    -0.07
     ruce
    -0.07
    ุà¹Ī
    -0.07
    apgolly
    -0.07
     serialVersionUID
    -0.07
    isclosed
    -0.07
    POSITIVE LOGITS
    lot
    0.07
    SEC
    0.06
     descent
    0.06
    aqu
    0.06
    antha
    0.06
     placement
    0.06
    descriptor
    0.06
    /exec
    0.06
    deal
    0.06
     erh
    0.06
    Activations Density 0.004%

    No Known Activations