© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 6-LLAMASCOPE-RES-32K
    6. 6469
    Prev
    Next
    INDEX
    Explanations

    code expressions and function calls in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flair
    -0.15
    лиÑĤ
    -0.14
    iem
    -0.14
    ¹
    -0.14
    onical
    -0.14
     escap
    -0.14
    onda
    -0.14
    edy
    -0.14
    ìĽ¨
    -0.14
    eon
    -0.14
    POSITIVE LOGITS
    uggle
    0.18
    aldi
    0.18
     uÄŁ
    0.15
     ÎijÏĢο
    0.15
    ibre
    0.14
    apı
    0.14
    enger
    0.14
    ="<?=$
    0.14
    aldo
    0.14
    incip
    0.14
    Activations Density 0.263%

    No Known Activations