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. 10-LLAMASCOPE-RES-32K
    6. 20509
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usan
    -0.14
    بÙĬÙĨ
    -0.13
    _UNSIGNED
    -0.13
    .Stage
    -0.13
    iod
    -0.13
     [
    -0.12
    ÙĪØ§Ø¡
    -0.12
    оÑģ
    -0.12
    _OPT
    -0.12
    \↵
    -0.12
    POSITIVE LOGITS
    .scalablytyped
    0.14
    /WebAPI
    0.14
    ifton
    0.14
    onne
    0.13
     âĶľ
    0.13
    esiyle
    0.13
    ascript
    0.13
    yle
    0.13
    ülük
    0.12
     annon
    0.12
    Activations Density 0.279%

    No Known Activations