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. 29-LLAMASCOPE-RES-32K
    6. 17349
    Prev
    Next
    INDEX
    Explanations

    instances of the phrases "To Be" and "From To" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    String
    -0.33
    verse
    -0.28
    paring
    -0.24
    nerRadius
    -0.24
    flater
    -0.22
    variant
    -0.22
    grese
    -0.21
    pNet
    -0.21
    ProcAddress
    -0.20
    StringValue
    -0.20
    POSITIVE LOGITS
    scription
    0.29
    cor
    0.29
    tr
    0.28
    nov
    0.28
    spir
    0.27
    nova
    0.27
    xic
    0.26
    scriptions
    0.26
    ok
    0.26
    alth
    0.26
    Activations Density 0.088%

    No Known Activations