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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3177
    Prev
    Next
    INDEX
    Explanations

    references to gaming systems and their characteristics

    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
     ol
    -0.06
    abela
    -0.06
    Bid
    -0.06
    uo
    -0.06
    ipt
    -0.06
     Purch
    -0.06
     Bid
    -0.05
    alc
    -0.05
    ause
    -0.05
    indle
    -0.05
    POSITIVE LOGITS
    ODB
    0.07
    codegen
    0.07
    ourcem
    0.07
     ÑģеÑĤ
    0.06
    é¢ij次
    0.06
    hardt
    0.06
     factors
    0.06
    ERVER
    0.06
    otation
    0.06
    ynes
    0.06
    Activations Density 0.001%

    No Known Activations