© 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. 21-LLAMASCOPE-RES-32K
    11. 20664
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     themselves
    -0.35
    ç»ĻæĪij
    -0.29
     us
    -0.26
     itself
    -0.25
    让æĪij
    -0.24
     me
    -0.23
     мне
    -0.21
    us
    -0.21
     mij
    -0.20
     himself
    -0.19
    POSITIVE LOGITS
     ourselves
    0.87
    Ñħодим
    0.41
     our
    0.34
     abych
    0.34
    ours
    0.34
    ï¼ĮæĪij们
    0.32
     دارÛĮÙħ
    0.29
     мож
    0.29
     наÑĪиÑħ
    0.28
    —we
    0.28
    Activations Density 1.208%

    No Known Activations