© 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. 31-LLAMASCOPE-RES-32K
    11. 15096
    Prev
    Next
    INDEX
    Explanations

    information related to artists and their work, particularly focusing on exhibitions and career highlights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vij
    -0.15
    æ¥
    -0.15
     moduleId
    -0.14
    466
    -0.14
    apat
    -0.13
    asto
    -0.13
     Affero
    -0.13
    istr
    -0.13
     Yug
    -0.13
    brahim
    -0.13
    POSITIVE LOGITS
     John
    1.26
    John
    1.13
     JOHN
    1.09
     john
    1.03
     Johns
    0.93
    john
    0.91
     ÐĶжон
    0.85
     Johnston
    0.75
     Johnny
    0.71
    ohn
    0.70
    Activations Density 0.097%

    No Known Activations