© 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. 22-LLAMASCOPE-RES-32K
    11. 20668
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "can" and its various forms reflecting capability or possibility

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    dez
    -0.17
    anut
    -0.17
    spark
    -0.15
    bbe
    -0.14
    amiliar
    -0.14
    TintColor
    -0.14
    ecure
    -0.13
    инов
    -0.13
    ãĥ³ãĥĹ
    -0.13
    ãĤĤãģĹ
    -0.13
    POSITIVE LOGITS
     tell
    0.63
     Tell
    0.54
    tell
    0.51
     telling
    0.50
     tells
    0.50
    Tell
    0.49
     Tells
    0.43
     told
    0.40
    åijĬè¯ī
    0.35
    .tell
    0.32
    Activations Density 0.091%

    No Known Activations