© 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. 31-LLAMASCOPE-RES-32K
    11. 15009
    Prev
    Next
    INDEX
    Explanations

    terms related to military and global security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strup
    -0.13
    adle
    -0.13
     Retrofit
    -0.13
     thá»į
    -0.12
    elper
    -0.12
    IDI
    -0.12
     nguyá»ĩn
    -0.12
    roke
    -0.11
    byte
    -0.11
    .localized
    -0.11
    POSITIVE LOGITS
     smuggling
    0.44
     trafficking
    0.41
     smugg
    0.39
     traff
    0.37
     illicit
    0.37
     illegal
    0.35
     narcotics
    0.34
     criminal
    0.33
     drug
    0.33
     drugs
    0.32
    Activations Density 0.257%

    No Known Activations