© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 29730
    Prev
    Next
    INDEX
    Explanations

    instances of significant numerical values, medical terms, and references to scientific studies related to health and food safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    429
    -0.15
    à¥ģह
    -0.14
    vice
    -0.14
     Hitch
    -0.14
    928
    -0.14
     Enlight
    -0.14
    ernel
    -0.14
     vice
    -0.14
     Benson
    -0.14
     stere
    -0.14
    POSITIVE LOGITS
    celik
    0.17
    osate
    0.17
    yntax
    0.15
    ivas
    0.15
     alleged
    0.15
    /MPL
    0.15
    _FE
    0.15
     svob
    0.15
    acemark
    0.14
    ñas
    0.14
    Activations Density 0.360%

    No Known Activations