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. 4-LLAMASCOPE-RES-32K
    6. 31029
    Prev
    Next
    INDEX
    Explanations

    event handling functions and methods related to event propagation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iyat
    -0.14
    ysz
    -0.14
    warz
    -0.13
     deluxe
    -0.13
     åį
    -0.13
    atel
    -0.13
    ków
    -0.13
     Premi
    -0.13
     Sand
    -0.13
    wer
    -0.13
    POSITIVE LOGITS
    otti
    0.14
    erre
    0.14
    omba
    0.14
    ãĤ¤ãĤ¯
    0.14
     stump
    0.14
    ãĥ¼ãĥł
    0.14
    484
    0.13
    atural
    0.13
    αÏĤ
    0.13
    .owl
    0.13
    Activations Density 0.301%

    No Known Activations