© 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. 9-LLAMASCOPE-RES-32K
    11. 2208
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to morphisms and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isure
    -0.16
    /date
    -0.14
    /go
    -0.14
     rac
    -0.14
    ÎŁÎĿ
    -0.13
     Zeus
    -0.13
     wi
    -0.13
     Rac
    -0.13
    Snapshot
    -0.13
    fos
    -0.13
    POSITIVE LOGITS
    akov
    0.17
     *}
    0.15
    chin
    0.14
    خاÙĨÙĩ
    0.14
    robots
    0.14
     Benef
    0.14
    preter
    0.14
     Evan
    0.14
     skoro
    0.13
    ManagerInterface
    0.13
    Activations Density 0.112%

    No Known Activations