© 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. 20-LLAMASCOPE-RES-32K
    11. 20188
    Prev
    Next
    INDEX
    Explanations

    expressions of commitment to values and goals, particularly focusing on growth, development, and quality

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    á»ħ
    -0.16
    û
    -0.14
     dán
    -0.14
    .sponge
    -0.14
    moz
    -0.14
    ceb
    -0.14
     è³
    -0.13
    _ASSUME
    -0.13
    omid
    -0.13
    needed
    -0.13
    POSITIVE LOGITS
     excellence
    0.23
     improvement
    0.20
     privacy
    0.19
     quality
    0.18
     Excellence
    0.17
     principle
    0.17
     causes
    0.17
     detail
    0.17
     excel
    0.17
     providing
    0.16
    Activations Density 0.056%

    No Known Activations