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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 12092
    Prev
    Next
    INDEX
    Explanations

    references to breast cancer and related medical topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUS
    -0.18
    èĬ³
    -0.15
    nar
    -0.15
    ister
    -0.15
    xic
    -0.15
    getElement
    -0.14
    credit
    -0.14
    AccessType
    -0.14
     credit
    -0.14
    tron
    -0.14
    POSITIVE LOGITS
    feeding
    0.31
     milk
    0.29
     cancer
    0.28
    bone
    0.25
     Milk
    0.24
    fed
    0.23
     Cancer
    0.23
    feed
    0.23
    stroke
    0.21
    aurant
    0.21
    Activations Density 0.005%

    No Known Activations