© 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. 21713
    Prev
    Next
    INDEX
    Explanations

    references to control systems or mechanisms

    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
    äº
    -0.18
     colon
    -0.16
     emb
    -0.14
     bran
    -0.14
     Colon
    -0.14
    leep
    -0.14
    inou
    -0.14
    >{!!
    -0.13
    _intr
    -0.13
    -basket
    -0.13
    POSITIVE LOGITS
     ESC
    0.25
     RC
    0.24
     brush
    0.24
     Hobby
    0.24
     Brush
    0.23
    RC
    0.23
     brushed
    0.23
    ESC
    0.22
     rc
    0.22
    Brush
    0.22
    Activations Density 0.007%

    No Known Activations