© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 18474
    Prev
    Next
    INDEX
    Explanations

    references to automotive events and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosk
    -0.14
    chsel
    -0.14
    (AT
    -0.14
     Toshiba
    -0.13
    Å¡et
    -0.13
    ="__
    -0.13
    帯
    -0.13
    elda
    -0.13
    erase
    -0.13
    kie
    -0.13
    POSITIVE LOGITS
     Vintage
    0.27
     vintage
    0.26
     restoration
    0.25
     Classic
    0.24
     collector
    0.23
     classic
    0.23
     Conc
    0.23
    Vintage
    0.23
    Classic
    0.22
     conc
    0.22
    Activations Density 0.066%

    No Known Activations