© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 61645
    Prev
    Next
    INDEX
    Explanations

    references to charitable events and their associated causes

    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
    anou
    -0.06
    ylko
    -0.06
    achi
    -0.06
     ãģ¾
    -0.06
    ñ
    -0.06
    ån
    -0.06
    稿
    -0.06
     Narr
    -0.06
    ropy
    -0.06
     Oil
    -0.06
    POSITIVE LOGITS
     Broadway
    0.10
     ÑĤеаÑĤ
    0.08
     Actors
    0.08
    fung
    0.08
     theatre
    0.07
    аÑĢаÑĤ
    0.07
    atego
    0.07
    оÑĤе
    0.07
    izio
    0.07
     NYC
    0.07
    Activations Density 0.012%

    No Known Activations