© 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. 27941
    Prev
    Next
    INDEX
    Explanations

    references to directional guidance or orientation

    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
    MOOTH
    -0.15
    çŃĭ
    -0.15
    uel
    -0.15
    ãģĵãĤĵãģ«
    -0.15
    \Migration
    -0.15
    riel
    -0.15
    UEL
    -0.15
     Guar
    -0.14
    ardy
    -0.14
    åĮĸ
    -0.14
    POSITIVE LOGITS
     directions
    0.22
     direction
    0.21
    sha
    0.19
    direction
    0.19
     Directions
    0.19
    æĸ¹åIJij
    0.18
     Trends
    0.17
     напÑĢав
    0.16
    azzi
    0.16
     fl
    0.16
    Activations Density 0.198%

    No Known Activations