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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11900
    Prev
    Next
    INDEX
    Explanations

    references to breast cancer and related medical terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    AccessType
    -0.18
    OUS
    -0.15
    tron
    -0.15
     eof
    -0.15
    haf
    -0.14
    gers
    -0.14
    emez
    -0.14
    °
    -0.14
    ÎŃÏģ
    -0.13
    rine
    -0.13
    POSITIVE LOGITS
     milk
    0.26
     cancer
    0.24
    bone
    0.24
    aurant
    0.23
    feeding
    0.22
    aurants
    0.21
     Milk
    0.20
    stroke
    0.19
     Cancer
    0.18
    roke
    0.17
    Activations Density 0.006%

    No Known Activations