© 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. 15-LLAMASCOPE-RES-131K
    11. 88266
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific titles related to sports and competitions

    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
    isté
    -0.07
     mastur
    -0.07
    ä¸Ŀ
    -0.07
    ëł
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
    abr
    -0.06
    jde
    -0.06
    oble
    -0.06
    Tables
    -0.06
    074
    -0.06
    POSITIVE LOGITS
    ships
    0.08
    ship
    0.08
    dom
    0.08
    chaft
    0.07
    innen
    0.07
    SError
    0.07
    esktop
    0.07
    SHIP
    0.07
    ilver
    0.07
    ing
    0.07
    Activations Density 0.000%

    No Known Activations