© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 13507
    Prev
    Next
    INDEX
    Explanations

    references to protocols or procedures related to data management or event handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ã¶ÄŁ
    -0.15
    ->↵
    -0.13
    ",__
    -0.12
    )&&(
    -0.12
    ,{"
    -0.12
    âī¡âī¡
    -0.12
     somehow
    -0.12
     cuckold
    -0.11
    )&&
    -0.11
     diplom
    -0.11
    POSITIVE LOGITS
     |
    1.12
     |↵
    0.72
    |
    0.68
     |[
    0.57
    .|
    0.56
     |↵↵
    0.55
     |_
    0.54
     |\
    0.52
     |:
    0.51
     |/
    0.50
    Activations Density 0.274%

    No Known Activations