© 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. 21510
    Prev
    Next
    INDEX
    Explanations

    collective pronouns and references to group identity

    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
     èĩ
    -0.15
    ModifiedDate
    -0.14
    .intersection
    -0.14
    vailability
    -0.14
    lia
    -0.14
    eacher
    -0.14
    elez
    -0.14
    rowable
    -0.13
    -display
    -0.13
    ylvania
    -0.13
    POSITIVE LOGITS
     saw
    0.23
     witness
    0.23
     witnessed
    0.21
     witnesses
    0.20
     hear
    0.20
     witnessing
    0.20
     Witness
    0.19
     enter
    0.19
     learned
    0.19
    Witness
    0.19
    Activations Density 0.092%

    No Known Activations