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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2806
    Prev
    Next
    INDEX
    Explanations

    references to specific clubs and organizations

    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
     Florida
    -0.21
    Florida
    -0.21
     Bay
    -0.18
    bay
    -0.18
     NJ
    -0.17
     Wisconsin
    -0.17
     Jacksonville
    -0.16
     Michigan
    -0.16
    Bay
    -0.16
     Chrysler
    -0.16
    POSITIVE LOGITS
     Yorkshire
    0.39
     Leeds
    0.35
    York
    0.30
     York
    0.27
     YORK
    0.27
     york
    0.26
     Leipzig
    0.25
     Yorkers
    0.23
     Scarborough
    0.23
     Tulsa
    0.21
    Activations Density 0.087%

    No Known Activations