© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12602
    Prev
    Next
    INDEX
    Explanations

    logistical details and regulations regarding event participation and requirements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    efa
    -0.15
     almost
    -0.15
    omal
    -0.15
    amina
    -0.15
    Required
    -0.15
    middlewares
    -0.14
     Required
    -0.14
    ipop
    -0.14
    Ñĸз
    -0.14
    Expected
    -0.14
    POSITIVE LOGITS
     maximum
    0.54
    maximum
    0.49
     MAX
    0.47
     max
    0.46
     Maximum
    0.46
    Maximum
    0.46
    max
    0.43
    MAX
    0.42
     ìµľëĮĢ
    0.41
     Max
    0.40
    Activations Density 0.173%

    No Known Activations