© 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 EvalsExportsinterp-engineNEWAPI 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. 14422
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or exchanges

    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
     he
    -0.44
     он
    -0.39
     вÑĸн
    -0.38
     him
    -0.34
    ä»ĸ
    -0.32
     lui
    -0.29
     ê·¸ëĬĶ
    -0.28
    /he
    -0.25
     He
    -0.25
    ä¸Ī夫
    -0.24
    POSITIVE LOGITS
     himself
    0.52
     Himself
    0.34
     ÙĨÙģسÙĩ
    0.30
    /her
    0.29
     wife
    0.28
    /she
    0.27
     his
    0.26
     her
    0.23
    妻
    0.23
    his
    0.23
    Activations Density 0.608%

    No Known Activations