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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3682
    Prev
    Next
    INDEX
    Explanations

    terms related to structural components and functions associated with fortifications and military settings

    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
    æ³ķ人
    -0.19
    ApiClient
    -0.17
     Olsen
    -0.15
    fully
    -0.15
     Bren
    -0.15
    yum
    -0.14
    ruba
    -0.14
     cues
    -0.14
    XMLElement
    -0.14
    iag
    -0.14
    POSITIVE LOGITS
    (es
    0.16
    iband
    0.15
    ắc
    0.14
     vo
    0.14
    esc
    0.14
     NVIC
    0.14
    /raw
    0.14
    hooks
    0.13
    ASON
    0.13
    849
    0.13
    Activations Density 0.050%

    No Known Activations