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. 20-LLAMASCOPE-RES-32K
    6. 11325
    Prev
    Next
    INDEX
    Explanations

    terms related to quantities and copies of items, particularly in the context of media and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zdy
    -0.15
     uÄŁ
    -0.14
     Gust
    -0.14
    ameleon
    -0.14
    FIT
    -0.13
    togroup
    -0.13
    /dist
    -0.13
    arrass
    -0.13
    è»
    -0.13
     Simulator
    -0.13
    POSITIVE LOGITS
     of
    0.40
     cá»§a
    0.33
     thereof
    0.24
     versions
    0.22
     version
    0.21
    à¸Ĥà¸Ńà¸ĩ
    0.20
    /cop
    0.20
    of
    0.19
     à¸Ĥà¸Ńà¸ĩ
    0.18
    าà¸Ĥà¸Ńà¸ĩ
    0.18
    Activations Density 0.198%

    No Known Activations