© 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. 23-LLAMASCOPE-RES-32K
    11. 11428
    Prev
    Next
    INDEX
    Explanations

    terms related to sports and physical activities, particularly actions and outcomes in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rogers
    -0.15
    vik
    -0.15
    ocoder
    -0.15
     wid
    -0.14
    antar
    -0.14
    ÑĸÑĩ
    -0.14
    _sensitive
    -0.14
    .robot
    -0.14
    activ
    -0.14
     trip
    -0.14
    POSITIVE LOGITS
     ball
    0.66
     balls
    0.54
    ball
    0.53
     Ball
    0.51
    -ball
    0.49
    Ball
    0.47
    balls
    0.46
     BALL
    0.45
    çIJĥ
    0.44
    _ball
    0.44
    Activations Density 0.155%

    No Known Activations