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

    Neuronpedia

    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. 23-LLAMASCOPE-RES-32K
    11. 21514
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to direction and movement, particularly in the context of making progress or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auce
    -0.16
    loth
    -0.15
    yš
    -0.14
    λλη
    -0.13
    ortal
    -0.13
    åłĤ
    -0.13
    agle
    -0.13
    fait
    -0.13
    ORMAL
    -0.13
     Dah
    -0.12
    POSITIVE LOGITS
     direction
    1.43
     directions
    1.23
    direction
    1.20
     Direction
    1.17
    æĸ¹åIJij
    1.09
    Direction
    1.08
     Directions
    1.03
    -direction
    1.00
    _direction
    0.94
    Directions
    0.92
    Activations Density 0.351%

    No Known Activations