© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 25-LLAMASCOPE-RES-32K
    11. 12417
    Prev
    Next
    INDEX
    Explanations

    terms related to processes of establishment, development, and creation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aille
    -0.16
    aldi
    -0.15
    lyn
    -0.15
    auen
    -0.15
     repeat
    -0.14
    /current
    -0.14
    ryn
    -0.14
    cells
    -0.14
    308
    -0.14
    HZ
    -0.13
    POSITIVE LOGITS
    ification
    0.20
    à¹ģละà¸ģาร
    0.19
    /application
    0.17
    Indented
    0.17
    slaught
    0.17
    ovánÃŃ
    0.17
    ization
    0.16
    ation
    0.16
    inya
    0.16
    IZATION
    0.16
    Activations Density 0.216%

    No Known Activations