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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 7967
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zman
    -0.14
     [â̦]↵↵
    -0.12
    odial
    -0.12
    üml
    -0.12
    hle
    -0.12
    #
    -0.12
    FOUNDATION
    -0.11
    isex
    -0.11
    sembles
    -0.11
    loff
    -0.11
    POSITIVE LOGITS
     latter
    0.14
    ÅĻád
    0.13
    .bunifuFlatButton
    0.12
    -urlencoded
    0.12
    ã
    0.12
    .toFloat
    0.12
    ÛĮرÛĮ
    0.12
    implify
    0.12
    PointerException
    0.12
    .Selenium
    0.12
    Activations Density 1.553%

    No Known Activations