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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17645
    Prev
    Next
    INDEX
    Explanations

    significant scientific concepts, particularly related to chemical reactions and catalysts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¥Ĥà¤ķ
    -0.17
    /reference
    -0.15
    resp
    -0.15
     dra
    -0.14
     XCT
    -0.13
    óż
    -0.13
    ouser
    -0.13
     evacuate
    -0.13
     draft
    -0.13
    ouse
    -0.13
    POSITIVE LOGITS
     reactions
    0.52
     reaction
    0.49
     Reaction
    0.43
    åıįåºĶ
    0.40
    reaction
    0.39
    Reaction
    0.38
     react
    0.36
     ÑĢеак
    0.36
    _reaction
    0.34
     reacting
    0.32
    Activations Density 0.075%

    No Known Activations