© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 17978
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and notable individuals in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    öst
    -0.14
    ôt
    -0.13
    ãĤĵãģ¨
    -0.13
    yte
    -0.13
    uela
    -0.12
     likelihood
    -0.12
    iele
    -0.12
    idd
    -0.12
    ubo
    -0.12
    æĸ¹
    -0.12
    POSITIVE LOGITS
    们
    0.13
    Äįka
    0.13
    soever
    0.13
    inson
    0.13
    Elapsed
    0.13
    ɵ
    0.13
     ydk
    0.13
    egal
    0.13
    _QMARK
    0.12
    mie
    0.12
    Activations Density 0.134%

    No Known Activations