© 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. 12-LLAMASCOPE-RES-32K
    11. 25510
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and control flows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ends
    -0.17
    412
    -0.15
    /books
    -0.15
    Endpoint
    -0.15
    erset
    -0.14
    amente
    -0.14
    414
    -0.14
    opol
    -0.14
    zheimer
    -0.14
    ierz
    -0.14
    POSITIVE LOGITS
    æºĸ
    0.16
    ıklı
    0.15
    окол
    0.14
    á»Ļ
    0.14
    IENCE
    0.13
     Äijế
    0.13
    spm
    0.13
    ascript
    0.13
    alet
    0.13
    .rb
    0.13
    Activations Density 0.209%

    No Known Activations