© 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. 17907
    Prev
    Next
    INDEX
    Explanations

    technical terms and operations related to software programming

    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
    enko
    -0.17
    èļ
    -0.15
    ÙĨداÙĨ
    -0.15
     Drew
    -0.15
    acus
    -0.14
     rewritten
    -0.14
    ìĿµ
    -0.14
    /loading
    -0.13
     rounding
    -0.13
    .src
    -0.13
    POSITIVE LOGITS
     bulk
    0.26
     delete
    0.25
    delete
    0.23
     list
    0.23
     Bulk
    0.23
     Ping
    0.23
     patch
    0.23
     ping
    0.23
     close
    0.21
    bulk
    0.21
    Activations Density 0.107%

    No Known Activations