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 (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 20701
    Prev
    Next
    INDEX
    Explanations

    financial terms and figures related to taxation and income thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wire
    -0.16
    lexer
    -0.15
    wo
    -0.14
    fund
    -0.14
    vek
    -0.14
     Wire
    -0.14
    lon
    -0.14
     Reynolds
    -0.14
     set
    -0.14
     D
    -0.14
    POSITIVE LOGITS
    ilers
    0.15
    kish
    0.15
    éĺ¶
    0.15
    اÙī
    0.15
    iams
    0.15
    rive
    0.15
     âĵĺ
    0.15
    еÑģÑĤÑĮ
    0.15
    MouseMove
    0.14
     Eudicots
    0.14
    Activations Density 0.102%

    No Known Activations