© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 10166
    Prev
    Next
    INDEX
    Explanations

    mentions of products, brands, and their associated qualities or marketing strategies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    âĢ¦↵↵
    -0.18
    âĢ¦↵
    -0.17
    âĢ¦)
    -0.16
    âĢ¦
    -0.15
     âĢ¦↵↵
    -0.15
     handjob
    -0.14
     gangbang
    -0.14
     swingers
    -0.13
     breat
    -0.13
    âĢ¦âĢ¦
    -0.13
    POSITIVE LOGITS
     escorte
    0.15
     conseils
    0.15
    á»ĩn
    0.14
     à¸ģรà¸ģ
    0.14
     overposting
    0.14
    úsqueda
    0.13
    rrha
    0.13
    rowsable
    0.13
    íı°
    0.13
    Writes
    0.13
    Activations Density 4.902%

    No Known Activations