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. 30-LLAMASCOPE-RES-32K
    6. 4581
    Prev
    Next
    INDEX
    Explanations

    times and numerical values related to dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.53
    :
    -0.40
    (
    -0.38
    /
    -0.34
    [
    -0.31
    ↵↵
    -0.30
    "
    -0.29
    -
    -0.28
    :↵
    -0.26
    '
    -0.26
    POSITIVE LOGITS
    innen
    0.21
    -↵↵
    0.18
    -↵
    0.17
    ;:;:
    0.15
    )-
    0.14
     semiclass
    0.14
    adero
    0.14
    )|
    0.13
    .scalablytyped
    0.13
    UsageId
    0.13
    Activations Density 0.573%

    No Known Activations