Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 4567
    Prev
    Next
    INDEX
    Explanations

    references to the use and implications of face masks

    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
    avad
    -0.19
     Blade
    -0.15
    stag
    -0.14
    blade
    -0.14
    733
    -0.13
    adio
    -0.13
     tend
    -0.13
    ÐĽÐIJ
    -0.13
    pis
    -0.13
     entertaining
    -0.13
    POSITIVE LOGITS
     masks
    0.47
     mask
    0.45
     Masks
    0.43
    -mask
    0.35
     Mask
    0.35
     MASK
    0.34
    Mask
    0.33
    mask
    0.33
     face
    0.32
    .mask
    0.31
    Activations Density 0.050%

    No Known Activations