© 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. 15-LLAMASCOPE-RES-32K
    11. 24521
    Prev
    Next
    INDEX
    Explanations

    phrases related to cautionary statements about information disclosure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iverz
    -0.16
    arks
    -0.15
    ocracy
    -0.15
    FFE
    -0.14
     fires
    -0.14
    anne
    -0.14
    /per
    -0.14
     dem
    -0.14
     monot
    -0.14
    ôn
    -0.14
    POSITIVE LOGITS
    ìļ°ë¦¬
    0.15
    etter
    0.15
    åĬª
    0.14
    ãĤ¿ãĥ¼
    0.14
    axon
    0.14
     sao
    0.14
    oyer
    0.14
    PIO
    0.14
    å®Ī
    0.14
    -sensitive
    0.14
    Activations Density 0.038%

    No Known Activations