© 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. 56094
    Prev
    Next
    INDEX
    Explanations

    names of popular figures associated with entertainment and media

    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
    ucci
    -0.08
    Sharper
    -0.07
    ething
    -0.07
    UFFIX
    -0.07
    ÑģÑĮ
    -0.07
    ied
    -0.07
    ialog
    -0.07
    sons
    -0.07
    /method
    -0.07
    ceed
    -0.07
    POSITIVE LOGITS
    گاÙĩ
    0.08
    air
    0.07
    angered
    0.07
    /ref
    0.07
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.07
    ä¼į
    0.07
    й
    0.07
    ough
    0.07
    /Foundation
    0.06
    аÑĢÑĮ
    0.06
    Activations Density 0.088%

    No Known Activations