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. 21-LLAMASCOPE-RES-32K
    6. 17754
    Prev
    Next
    INDEX
    Explanations

    classifications or categorizations related to visas and their requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (NO
    -0.15
    -plugins
    -0.15
    NSIndexPath
    -0.15
     Bris
    -0.15
    anko
    -0.14
    etooth
    -0.14
    841
    -0.14
    033
    -0.13
    δα
    -0.13
     Koh
    -0.13
    POSITIVE LOGITS
    /Foundation
    0.16
    rex
    0.16
    akh
    0.15
     III
    0.14
    reira
    0.14
     dÄ±ÅŁÄ±
    0.14
    /component
    0.14
    /Branch
    0.14
    stan
    0.14
    रण
    0.14
    Activations Density 0.063%

    No Known Activations