© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 14760
    Prev
    Next
    INDEX
    Explanations

    code structure and organization cues, particularly in JavaScript-related contexts

    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
    éģ¸æīĭ
    -0.15
    VOID
    -0.14
    ога
    -0.13
    fy
    -0.13
    Ĥæķ°
    -0.13
     Pruitt
    -0.13
    iggers
    -0.13
    het
    -0.13
    _traits
    -0.13
    strain
    -0.13
    POSITIVE LOGITS
     function
    1.01
    function
    0.84
    (function
    0.69
    	function
    0.68
     Function
    0.61
    ,function
    0.60
    =function
    0.58
    -function
    0.56
     functions
    0.53
    :function
    0.53
    Activations Density 0.273%

    No Known Activations