© 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. 18-LLAMASCOPE-RES-32K
    6. 12244
    Prev
    Next
    INDEX
    Explanations

    coding-related keywords and structures associated with options and settings in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gow
    -0.15
    ixe
    -0.15
    stras
    -0.15
    ç¦ģ
    -0.14
    ilder
    -0.14
    rün
    -0.14
    aravel
    -0.14
    vá
    -0.14
    Charsets
    -0.14
    erap
    -0.14
    POSITIVE LOGITS
    able
    0.16
    ief
    0.15
     inverted
    0.15
    igy
    0.15
     rubber
    0.14
     skinny
    0.14
    ible
    0.14
    anda
    0.14
    Pot
    0.13
    arda
    0.13
    Activations Density 0.182%

    No Known Activations