© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21150
    Prev
    Next
    INDEX
    Explanations

    phrases related to attendance and participation in events or shows

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    bler
    -0.14
    upo
    -0.13
    175
    -0.13
    .slim
    -0.12
    ulse
    -0.12
     Sap
    -0.12
    /Search
    -0.12
     tÄĽ
    -0.12
    plete
    -0.12
    .tbl
    -0.12
    POSITIVE LOGITS
     show
    1.08
    show
    0.96
    -show
    0.94
     Show
    0.91
     SHOW
    0.86
    Show
    0.85
    _show
    0.85
    .show
    0.83
    SHOW
    0.80
     shows
    0.77
    Activations Density 0.325%

    No Known Activations