© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 8684
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, specifically modifiers and return types within function and variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibri
    -0.15
    utherland
    -0.15
    zman
    -0.15
    ieee
    -0.14
    çŃĴ
    -0.14
    vil
    -0.14
    assel
    -0.14
    ylon
    -0.14
    isoft
    -0.14
    veloper
    -0.14
    POSITIVE LOGITS
     int
    0.51
    int
    0.34
    	int
    0.31
    (int
    0.29
     double
    0.28
    =int
    0.26
    [int
    0.25
    .int
    0.25
     float
    0.25
    :int
    0.23
    Activations Density 0.059%

    No Known Activations