© 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. 19648
    Prev
    Next
    INDEX
    Explanations

    activities or actions related to creativity, organization, or how to improve skills and performance

    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
    rava
    -0.13
     somehow
    -0.13
    brtc
    -0.13
    åŀ
    -0.13
    SetValue
    -0.13
    plet
    -0.13
    swire
    -0.13
    reminder
    -0.13
     provision
    -0.12
    Chance
    -0.12
    POSITIVE LOGITS
     your
    0.30
     yourself
    0.29
    your
    0.27
    ä½łçļĦ
    0.23
     effectively
    0.22
     YOUR
    0.21
    Your
    0.20
     Yourself
    0.19
     tip
    0.19
     ваÑĪ
    0.19
    Activations Density 0.301%

    No Known Activations