© 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. 442
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and development practices

    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
     without
    -0.15
    ison
    -0.15
    gent
    -0.15
     following
    -0.14
    clid
    -0.14
    ultz
    -0.13
     decisive
    -0.13
    uibModal
    -0.13
    without
    -0.13
    raž
    -0.13
    POSITIVE LOGITS
     costly
    0.27
     expensive
    0.23
    ç¹ģ
    0.22
     necessarily
    0.21
    же
    0.20
    มาà¸ģมาย
    0.20
    additional
    0.19
     дополниÑĤелÑĮ
    0.19
    ecessarily
    0.19
     navÃŃc
    0.19
    Activations Density 0.415%

    No Known Activations