© 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. 26-LLAMASCOPE-RES-32K
    11. 17980
    Prev
    Next
    INDEX
    Explanations

    phrases related to music recording and playback technology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     COVID
    -0.22
     userID
    -0.21
     UserID
    -0.20
     eBook
    -0.20
    userID
    -0.20
     McKay
    -0.20
     eBooks
    -0.19
    COVID
    -0.18
    TypeID
    -0.18
    .userID
    -0.17
    POSITIVE LOGITS
     Usa
    0.28
     Cbd
    0.27
     Www
    0.27
    ’S
    0.26
     Cd
    0.26
     Hp
    0.26
     Pdf
    0.26
     Tv
    0.25
     Hd
    0.25
     Pc
    0.23
    Activations Density 0.250%

    No Known Activations