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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 17986
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategy games and their mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñıгом
    -0.14
     ÐļÑĢÑĸм
    -0.12
    ï¼Į以åıĬ
    -0.12
    жÑĥ
    -0.12
    ãģŁãĤĬ
    -0.12
    Ķëĭ¤
    -0.11
    uming
    -0.11
    impan
    -0.11
    одаÑĢ
    -0.10
    ëĵł
    -0.10
    POSITIVE LOGITS
     but
    1.12
    but
    0.90
     nhưng
    0.84
     но
    0.73
     BUT
    0.73
    ä½Ĩ
    0.72
    _but
    0.71
     pero
    0.70
     maar
    0.69
    ï¼Įä½Ĩ
    0.69
    Activations Density 4.282%

    No Known Activations