© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 22966
    Prev
    Next
    INDEX
    Explanations

    elements related to computer programming syntax, particularly in languages like JavaScript or Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prise
    -0.13
    #ab
    -0.13
    svp
    -0.12
    #af
    -0.12
     |_
    -0.12
    .au
    -0.11
    edith
    -0.11
     ë§Īë²ķ
    -0.11
    //{{
    -0.11
    lds
    -0.11
    POSITIVE LOGITS
     ÅĻÃŃj
    0.16
    OKIE
    0.15
    ENARIO
    0.14
    REATED
    0.14
    iÅ¡tÄĽ
    0.13
    ednou
    0.13
    ázÃŃ
    0.13
    ãģĵãģĿ
    0.13
     bÅĻez
    0.12
    ERRU
    0.12
    Activations Density 2.764%

    No Known Activations