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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13773
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols in code or technical documents

    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
    ...↵
    -0.28
    ↵
    -0.28
    (
    -0.27
    [
    -0.27
    "
    -0.27
    s
    -0.26
    the
    -0.24
    i
    -0.24
    and
    -0.22
    :
    -0.22
    POSITIVE LOGITS
     ↵
    0.19
    .ISupportInitialize
    0.16
    /=
    0.15
     ...)↵
    0.15
    tree
    0.14
    ÑĤÑĢо
    0.14
    ).[
    0.14
    /,
    0.13
    uses
    0.13
    alto
    0.13
    Activations Density 0.247%

    No Known Activations