Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 2091
    Prev
    Next
    INDEX
    Explanations

    references to extremist groups

    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
    apolis
    -0.16
    رÙĪØª
    -0.14
    sville
    -0.14
    alars
    -0.13
    inox
    -0.13
    occo
    -0.13
    ADX
    -0.13
    ÙĬÙĦا
    -0.13
    ecko
    -0.13
    (P
    -0.13
    POSITIVE LOGITS
    -Qaeda
    0.26
    -'
    0.23
    -Q
    0.22
    aa
    0.22
     Qaeda
    0.22
    -Z
    0.21
    -Jul
    0.21
    -N
    0.21
    -J
    0.21
    -Sh
    0.21
    Activations Density 0.017%

    No Known Activations