© 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. 2-LLAMASCOPE-RES-32K
    11. 17914
    Prev
    Next
    INDEX
    Explanations

    phrases or instances that emphasize the word "These."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zano
    -0.17
    ants
    -0.15
    ekil
    -0.15
    loff
    -0.15
    dden
    -0.14
    enos
    -0.14
     strict
    -0.14
    èħ¾
    -0.14
    oter
    -0.14
    ubar
    -0.14
    POSITIVE LOGITS
    oretical
    0.20
    ĭ
    0.15
    embre
    0.15
    aml
    0.15
    curity
    0.14
     Byrne
    0.14
    urma
    0.14
     Plug
    0.14
     Aviv
    0.14
    oret
    0.13
    Activations Density 0.026%

    No Known Activations