© 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. 17-LLAMASCOPE-RES-131K
    11. 78570
    Prev
    Next
    INDEX
    Explanations

    details related to sports tournaments and game rules

    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
    ól
    -0.07
    IGHL
    -0.06
    peak
    -0.06
     puzzle
    -0.05
     Braun
    -0.05
    omik
    -0.05
     peak
    -0.05
     metam
    -0.05
     rowspan
    -0.05
    åĶ
    -0.05
    POSITIVE LOGITS
    MAND
    0.08
     format
    0.08
    IFO
    0.07
    åĨ³
    0.07
    format
    0.07
    ordin
    0.07
    Format
    0.07
     single
    0.07
    -format
    0.07
     tie
    0.07
    Activations Density 0.008%

    No Known Activations