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. 3-LLAMASCOPE-RES-32K
    6. 16366
    Prev
    Next
    INDEX
    Explanations

    syntax elements and patterns used in regular expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phem
    -0.15
     LENG
    -0.15
    .ButterKnife
    -0.14
    rack
    -0.14
    alin
    -0.14
    ogne
    -0.14
    ettings
    -0.14
    usercontent
    -0.13
    uje
    -0.13
    alez
    -0.13
    POSITIVE LOGITS
    berman
    0.18
    mour
    0.16
    ãģŀ
    0.14
    δαÏĤ
    0.14
    adar
    0.14
     hardware
    0.14
     chia
    0.14
    esor
    0.14
    lez
    0.14
    .learn
    0.14
    Activations Density 0.073%

    No Known Activations