© 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. 13-LLAMASCOPE-RES-32K
    11. 18471
    Prev
    Next
    INDEX
    Explanations

    references to specific regulations or guidelines in a structured context, such as financial or aviation safety documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SAFE
    -0.16
    zik
    -0.15
    ạm
    -0.15
    AlmostEqual
    -0.15
    iband
    -0.15
    wright
    -0.15
    zek
    -0.14
    Hier
    -0.14
    .lua
    -0.14
    нÑĸв
    -0.14
    POSITIVE LOGITS
    acs
    0.17
     thẳng
    0.13
    edad
    0.13
     lá»ĭch
    0.13
    yle
    0.13
     Straight
    0.13
    ylon
    0.13
    agrams
    0.13
    aze
    0.13
    ision
    0.13
    Activations Density 0.155%

    No Known Activations