© 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 EvalsExportsAPI 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. 12553
    Prev
    Next
    INDEX
    Explanations

    references to large quantities, especially involving measurements and production statistics

    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
    sink
    -0.16
    atz
    -0.15
     mile
    -0.15
    üz
    -0.15
     miles
    -0.15
     kilometers
    -0.15
     Mur
    -0.15
    åĢī
    -0.15
     bile
    -0.14
     sank
    -0.14
    POSITIVE LOGITS
     cubic
    0.46
     Cub
    0.36
     cub
    0.30
     кÑĥб
    0.28
     cube
    0.26
    ubic
    0.26
     Lit
    0.25
    lit
    0.25
     Gall
    0.24
     cubes
    0.24
    Activations Density 0.074%

    No Known Activations