© 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. 26-LLAMASCOPE-RES-32K
    11. 17959
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Rated
    -0.18
    Robert
    -0.17
     Robert
    -0.16
     Rum
    -0.16
     Rat
    -0.15
     Roo
    -0.15
    RATE
    -0.15
    Rated
    -0.15
    Ron
    -0.15
    heim
    -0.15
    POSITIVE LOGITS
     render
    1.25
     rendering
    1.14
    render
    1.13
     Render
    1.11
     rendered
    1.08
     renders
    1.05
    Render
    1.04
    -render
    1.01
    .render
    1.01
     Rendering
    0.98
    Activations Density 0.030%

    No Known Activations