© 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. 27-LLAMASCOPE-RES-32K
    11. 5983
    Prev
    Next
    INDEX
    Explanations

    specific performance metrics and data-related content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ubby
    -0.14
    enci
    -0.14
    оби
    -0.14
    oblin
    -0.13
    ctic
    -0.13
    FAULT
    -0.13
    -tm
    -0.13
    ayi
    -0.13
    GLfloat
    -0.12
    Connell
    -0.12
    POSITIVE LOGITS
     Cam
    1.41
     cam
    1.38
    Cam
    1.35
     CAM
    1.24
    cam
    1.20
    CAM
    1.13
     Cambridge
    1.07
    .cam
    1.06
    _cam
    1.05
     Cameron
    1.04
    Activations Density 0.090%

    No Known Activations