© 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. 22-LLAMASCOPE-RES-32K
    11. 765
    Prev
    Next
    INDEX
    Explanations

    key historical events related to baseball player Ted Williams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eldo
    -0.18
    xef
    -0.15
    .@
    -0.15
    ainen
    -0.15
    dda
    -0.15
    ãĥ©ãĥ³ãĥī
    -0.15
    ovu
    -0.14
    oldur
    -0.14
    ItemAt
    -0.14
     programm
    -0.14
    POSITIVE LOGITS
     Babe
    0.17
     pitching
    0.16
     Cyan
    0.15
     Candle
    0.15
     CY
    0.15
     cycl
    0.15
     bean
    0.15
     Rosen
    0.14
    enz
    0.14
     pitched
    0.14
    Activations Density 0.075%

    No Known Activations