© 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. 8-LLAMASCOPE-RES-32K
    11. 29314
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a focus on attention and directed actions involving collaboration or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ross
    -0.17
     åº
    -0.15
    undy
    -0.14
    SORT
    -0.14
    .vaadin
    -0.14
    iji
    -0.13
     Lip
    -0.13
    361
    -0.13
    alg
    -0.13
    quet
    -0.13
    POSITIVE LOGITS
    ekler
    0.15
    imli
    0.15
    ãģĬãĤĬ
    0.15
    earing
    0.14
    vale
    0.14
     دÙĪÙĨ
    0.14
    ê°IJ
    0.14
    _tabs
    0.13
     اÛĮÙĨجا
    0.13
    äng
    0.13
    Activations Density 0.092%

    No Known Activations