© 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 EvalsExportsinterp-engineNEWAPI 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. 74090
    Prev
    Next
    INDEX
    Explanations

    references to competitive sports events and race results

    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
    iet
    -0.06
    ãĤ·ãĥ¼
    -0.06
    æĻ´
    -0.06
    opoulos
    -0.06
    IIIK
    -0.06
    PU
    -0.06
    viewer
    -0.06
     imper
    -0.06
    alc
    -0.06
    Metro
    -0.06
    POSITIVE LOGITS
    edl
    0.09
    IMIT
    0.07
    ignum
    0.07
    ouro
    0.07
    _COMPAT
    0.07
    ICON
    0.07
     Hess
    0.06
    agt
    0.06
    ebin
    0.06
    eyJ
    0.06
    Activations Density 0.032%

    No Known Activations