© 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. 17-LLAMASCOPE-RES-32K
    11. 23924
    Prev
    Next
    INDEX
    Explanations

    events related to sports gameplay and officiating decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicopt
    -0.15
     sadd
    -0.15
     ध
    -0.14
    loquent
    -0.14
    PÅĻi
    -0.14
    .dk
    -0.14
    idual
    -0.13
    etas
    -0.13
    ACHI
    -0.13
    à¹Ģà¸īà¸ŀาะ
    -0.13
    POSITIVE LOGITS
     ruled
    0.18
     replay
    0.17
     ruling
    0.17
    igar
    0.16
     offic
    0.16
    fra
    0.16
     Penalty
    0.15
     penalty
    0.14
    sei
    0.14
    refs
    0.14
    Activations Density 0.032%

    No Known Activations