© 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. 84407
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to sports teams and figures

    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
    anson
    -0.07
    atten
    -0.07
    arius
    -0.07
    obo
    -0.07
     hes
    -0.06
    ammers
    -0.06
    acted
    -0.06
    ideon
    -0.06
    amos
    -0.06
    uled
    -0.06
    POSITIVE LOGITS
     colleagues
    0.10
     colleague
    0.08
     peers
    0.08
     counterpart
    0.08
     counterparts
    0.07
     contempor
    0.07
    igu
    0.06
     connections
    0.06
     partners
    0.06
     friends
    0.06
    Activations Density 0.073%

    No Known Activations