© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 19018
    Prev
    Next
    INDEX
    Explanations

    concepts related to barriers and restrictions, both physical and metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leness
    -0.14
    ovny
    -0.14
    .rc
    -0.13
    pole
    -0.13
    lix
    -0.13
    ÑĢÑĥд
    -0.13
     benches
    -0.13
     Tray
    -0.13
     punished
    -0.13
    .yy
    -0.13
    POSITIVE LOGITS
     walls
    0.55
     wall
    0.50
     barrier
    0.49
     barriers
    0.47
     Walls
    0.43
    walls
    0.43
    wall
    0.42
     WALL
    0.40
    -wall
    0.38
     Barrier
    0.36
    Activations Density 0.201%

    No Known Activations