© 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. 11-LLAMASCOPE-RES-32K
    11. 28654
    Prev
    Next
    INDEX
    Explanations

    elements related to web page styling and layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (ang
    -0.15
    olini
    -0.15
    ationally
    -0.14
    rlen
    -0.14
    Query
    -0.14
     Pas
    -0.14
    odata
    -0.14
    ock
    -0.14
    ait
    -0.14
     patch
    -0.13
    POSITIVE LOGITS
    unc
    0.16
    -svg
    0.15
    -collapse
    0.15
    lut
    0.13
    én
    0.13
    ught
    0.13
     YYS
    0.13
    ãĤ«ãĥĨ
    0.13
    eel
    0.13
    289
    0.13
    Activations Density 0.004%

    No Known Activations