© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 31045
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a domain or field of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏĢη
    -0.17
    dy
    -0.15
    ross
    -0.15
    celand
    -0.15
    apping
    -0.14
    SF
    -0.14
     traced
    -0.14
    _reserve
    -0.14
     pred
    -0.13
    Constraints
    -0.13
    POSITIVE LOGITS
    Ú¯ÛĮر
    0.15
    tron
    0.15
    ãĥ¼ãĥī
    0.15
     Hüs
    0.15
    mmc
    0.14
     (~(
    0.14
    309
    0.14
     Audio
    0.14
    Shapes
    0.14
    694
    0.13
    Activations Density 0.005%

    No Known Activations