© 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. 4627
    Prev
    Next
    INDEX
    Explanations

    references to personal role models and influences

    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
    ùi
    -0.17
    loy
    -0.15
    íħ
    -0.15
    681
    -0.15
     reputation
    -0.15
    ãĥ¼ãĤ¿ãĥ¼
    -0.15
    ifax
    -0.14
    çıį
    -0.14
    locator
    -0.14
    _IB
    -0.14
    POSITIVE LOGITS
     heroes
    0.50
     hero
    0.49
     idol
    0.47
     idols
    0.45
     Heroes
    0.40
    hero
    0.40
    heroes
    0.40
     inspiration
    0.40
     Hero
    0.38
     HERO
    0.36
    Activations Density 0.123%

    No Known Activations