© 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. 16-LLAMASCOPE-RES-32K
    11. 21098
    Prev
    Next
    INDEX
    Explanations

    statements or questions involving hypothetical scenarios or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reo
    -0.15
    Ãłu
    -0.14
    camel
    -0.14
    åIJĪãĤıãģĽ
    -0.14
    amac
    -0.14
    atta
    -0.14
    ấp
    -0.14
    lei
    -0.13
    upal
    -0.13
    inet
    -0.13
    POSITIVE LOGITS
    oller
    0.18
    loadModel
    0.15
    ushman
    0.15
    emiz
    0.15
     ìŀĪëĭ¤ê³ł
    0.14
    ABCDEFGHI
    0.14
    onda
    0.14
    èĪ
    0.14
    .xtext
    0.14
     ÙħØ«ÙĦا
    0.14
    Activations Density 0.099%

    No Known Activations