© 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. 31-LLAMASCOPE-RES-32K
    11. 14047
    Prev
    Next
    INDEX
    Explanations

    terms related to holistic healing and alternative medicine

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    uentes
    -0.16
    imientos
    -0.16
    eração
    -0.15
    ERO
    -0.14
    mana
    -0.14
    illez
    -0.14
    itorio
    -0.14
    į°
    -0.14
    ero
    -0.14
    lier
    -0.14
    POSITIVE LOGITS
    ic
    0.96
    ics
    0.64
    ically
    0.56
    IC
    0.50
    icc
    0.46
    (ic
    0.46
    icl
    0.43
     ic
    0.43
    icity
    0.41
    iÄĩ
    0.41
    Activations Density 0.047%

    No Known Activations