© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28159
    Prev
    Next
    INDEX
    Explanations

    words related to reporting and statements from officials

    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
     Circus
    -0.14
    обов
    -0.14
    Physical
    -0.14
     Occupational
    -0.13
    eldig
    -0.13
    ennie
    -0.13
    _NC
    -0.13
    кÑĥÑĢ
    -0.13
    ermal
    -0.13
    habit
    -0.13
    POSITIVE LOGITS
    ès
    0.16
    ifr
    0.16
    aleb
    0.16
    Æ¡n
    0.14
    igham
    0.14
    iets
    0.14
     Kelley
    0.14
    ESIS
    0.14
    ash
    0.13
     subsidi
    0.13
    Activations Density 0.273%

    No Known Activations