© 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. 29-LLAMASCOPE-RES-32K
    11. 101
    Prev
    Next
    INDEX
    Explanations

    positive descriptors indicating helpfulness or utility

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    edb
    -0.20
    alla
    -0.17
    iah
    -0.17
    edBy
    -0.17
    Ìĥ
    -0.17
    ed
    -0.16
    ALLE
    -0.15
    rov
    -0.15
    æ£ļ
    -0.15
    anian
    -0.15
    POSITIVE LOGITS
    ness
    0.41
    lest
    0.34
    NESS
    0.31
    mente
    0.28
    s
    0.24
    nes
    0.24
     enough
    0.24
    /use
    0.23
    /help
    0.23
    -looking
    0.22
    Activations Density 0.087%

    No Known Activations