© 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. 16529
    Prev
    Next
    INDEX
    Explanations

    player statistics and performance indicators 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
    ikon
    -0.06
    ãĥ«ãĥķ
    -0.06
    VERRIDE
    -0.06
     Bloc
    -0.06
     bloc
    -0.06
     Bros
    -0.05
     verst
    -0.05
     Roc
    -0.05
     Yoshi
    -0.05
    enaries
    -0.05
    POSITIVE LOGITS
    agara
    0.08
    ahun
    0.08
     Casc
    0.07
    ÑĶÑĪ
    0.07
    .rt
    0.07
    iram
    0.07
     sle
    0.07
    Sock
    0.07
    Hierarchy
    0.07
    pec
    0.07
    Activations Density 0.021%

    No Known Activations