© 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. 6633
    Prev
    Next
    INDEX
    Explanations

    specific programming functions and variable assignments

    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
    s
    -0.58
    Ùĩ
    -0.27
    ska
    -0.24
    sah
    -0.22
    sburg
    -0.20
    sing
    -0.19
    sik
    -0.19
    sie
    -0.19
    न
    -0.19
    sak
    -0.19
    POSITIVE LOGITS
    urma
    0.16
    çok
    0.15
    arat
    0.15
    atre
    0.15
    zelf
    0.15
    à¹ĥà¸Ī
    0.14
    acente
    0.14
    vů
    0.14
     tầm
    0.14
    theless
    0.14
    Activations Density 0.168%

    No Known Activations