Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5228
    Prev
    Next
    INDEX
    Explanations

    information related to sports player transfers and career events

    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
     onCancelled
    -0.07
    leÅŁik
    -0.07
    <?↵
    -0.07
    currently
    -0.07
    orgot
    -0.07
    edicine
    -0.07
    .Images
    -0.07
    oser
    -0.07
    á»ĩ
    -0.06
    /gpl
    -0.06
    POSITIVE LOGITS
    È
    0.08
    aily
    0.06
    isl
    0.06
    íĭĢ
    0.06
    zion
    0.06
    utar
    0.06
    erc
    0.05
     Jong
    0.05
    .ga
    0.05
    ps
    0.05
    Activations Density 0.018%

    No Known Activations