© 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. 19-LLAMASCOPE-RES-32K
    11. 32143
    Prev
    Next
    INDEX
    Explanations

    elements of programming or code snippets related to database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warsaw
    -0.15
    aukee
    -0.15
     Mah
    -0.15
    ráž
    -0.15
    brids
    -0.14
    athers
    -0.14
     b
    -0.14
    поÑĢ
    -0.14
     Floyd
    -0.14
    andles
    -0.14
    POSITIVE LOGITS
     Flask
    0.28
     flask
    0.24
     SQLAlchemy
    0.19
    .blue
    0.16
    fl
    0.16
     WTF
    0.16
     werk
    0.16
    (Fl
    0.16
     Werk
    0.15
     Cornwall
    0.15
    Activations Density 0.007%

    No Known Activations