© 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. 24-LLAMASCOPE-RES-32K
    11. 20261
    Prev
    Next
    INDEX
    Explanations

    phrases related to the collection and handling of personally identifiable information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.16
    ubern
    -0.15
     haz
    -0.14
     immediate
    -0.14
    riad
    -0.14
    duct
    -0.14
     Hüs
    -0.14
    pearance
    -0.14
     ÐĴоÑĤ
    -0.14
    eko
    -0.13
    POSITIVE LOGITS
     interact
    0.19
    Supply
    0.18
     Supply
    0.18
     filling
    0.18
     supply
    0.17
    interaction
    0.17
    upply
    0.17
    å¡«
    0.16
    .Input
    0.16
    supply
    0.15
    Activations Density 0.041%

    No Known Activations