© 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. 4-LLAMASCOPE-RES-32K
    11. 18279
    Prev
    Next
    INDEX
    Explanations

    instances of the word "continue" and its variations, indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attendance
    -0.14
    fen
    -0.14
    kf
    -0.14
    à¹Īà¸ĩà¸Ĥ
    -0.14
    AMED
    -0.14
    ouched
    -0.13
    713
    -0.13
    inspection
    -0.13
    å°¾
    -0.13
     rau
    -0.13
    POSITIVE LOGITS
    ournal
    0.16
    earch
    0.16
     Cup
    0.14
    ä¹ĺ
    0.14
    rij
    0.14
    .readString
    0.14
     harmony
    0.14
    aya
    0.14
    عر
    0.14
    htdocs
    0.13
    Activations Density 0.195%

    No Known Activations