© 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. 19910
    Prev
    Next
    INDEX
    Explanations

    references to social dynamics and community activities

    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
    onis
    -0.20
    ONO
    -0.17
    寧
    -0.16
     Gow
    -0.16
    rites
    -0.16
    cu
    -0.15
    onu
    -0.15
    vro
    -0.14
    mdir
    -0.14
    WR
    -0.14
    POSITIVE LOGITS
     nothing
    0.48
    nothing
    0.40
     Nothing
    0.39
     familiar
    0.37
     NOTHING
    0.35
    Nothing
    0.34
     familiarity
    0.29
     Fam
    0.29
     nichts
    0.27
     ниÑĩего
    0.27
    Activations Density 0.125%

    No Known Activations