© 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. 28-LLAMASCOPE-RES-32K
    11. 24585
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to rankings, measurements, and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brew
    -0.20
    276
    -0.17
    XF
    -0.15
     Scientist
    -0.15
    CHASE
    -0.15
    dateFormat
    -0.14
     Hunt
    -0.14
    ansi
    -0.14
     Cary
    -0.14
    thrown
    -0.14
    POSITIVE LOGITS
    inker
    0.24
     placer
    0.23
     rais
    0.23
     exerc
    0.23
    clud
    0.22
     impro
    0.21
    aller
    0.21
    serter
    0.21
    OUNTER
    0.21
    isher
    0.21
    Activations Density 0.317%

    No Known Activations