© 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. 21-LLAMASCOPE-RES-32K
    11. 4732
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with strangeness or oddity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    inker
    -0.15
    noinspection
    -0.15
    mund
    -0.14
    inous
    -0.14
    DIR
    -0.13
    thed
    -0.13
    Embedded
    -0.13
    imid
    -0.13
    pany
    -0.13
    enn
    -0.13
    POSITIVE LOGITS
    ities
    0.26
    -shaped
    0.24
     shaped
    0.20
    ly
    0.18
    ball
    0.18
    à¹Ģà¸ģà¸Ńร
    0.18
    -looking
    0.18
    -ball
    0.18
    ily
    0.17
    /we
    0.17
    Activations Density 0.065%

    No Known Activations