© 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. 20-LLAMASCOPE-RES-32K
    11. 7011
    Prev
    Next
    INDEX
    Explanations

    references to various medical conditions and disorders

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ED
    -0.20
    EA
    -0.19
    ecz
    -0.19
     Edgar
    -0.19
    ед
    -0.18
     Eddie
    -0.18
    éd
    -0.17
    ead
    -0.17
    edef
    -0.17
     Echo
    -0.17
    POSITIVE LOGITS
     Bentley
    0.25
     Bent
    0.23
     ben
    0.22
     Benson
    0.22
     Ben
    0.22
     benz
    0.21
     Benz
    0.20
    Ben
    0.20
     Benny
    0.20
     Benn
    0.19
    Activations Density 0.030%

    No Known Activations