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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20259
    Prev
    Next
    INDEX
    Explanations

    the word "that" and its variations in context

    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
     THAT
    -0.15
    ellar
    -0.14
    isque
    -0.14
    thon
    -0.14
    tron
    -0.14
    iv
    -0.13
    ey
    -0.13
    oidal
    -0.13
    uD
    -0.13
     saja
    -0.13
    POSITIVE LOGITS
     ones
    0.23
     of
    0.21
     của
    0.21
    ÃĹ↵↵
    0.18
    bedo
    0.18
    cher
    0.18
    à¤Ĥध
    0.16
    oa
    0.16
    ones
    0.15
    zelf
    0.15
    Activations Density 0.050%

    No Known Activations