© 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. 15-LLAMASCOPE-RES-32K
    11. 16574
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terminology related to cultural or historical subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ephir
    -0.19
    adeon
    -0.14
    isphere
    -0.14
    oru
    -0.14
    agraph
    -0.13
     poste
    -0.13
    abyte
    -0.12
    ifice
    -0.12
    acio
    -0.12
    exus
    -0.12
    POSITIVE LOGITS
     Wrapped
    0.15
    ills
    0.15
    ioned
    0.15
     bá»ģ
    0.14
    halb
    0.14
    (sp
    0.13
     Suspension
    0.13
    va
    0.12
     Www
    0.12
    надлеж
    0.12
    Activations Density 0.382%

    No Known Activations