© 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. 16-LLAMASCOPE-RES-32K
    11. 19292
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and modal verbs indicating possibility or obligation

    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
    éric
    -0.17
    stÅĻÃŃ
    -0.16
    ãĤ·ãĤ¢
    -0.15
    ysa
    -0.15
    missible
    -0.14
    bound
    -0.14
    ãĤ¤ãĤ¹
    -0.14
    ying
    -0.14
    ces
    -0.14
    iders
    -0.14
    POSITIVE LOGITS
    ustin
    0.18
    uder
    0.15
    buz
    0.15
    ائ
    0.14
    amak
    0.14
     Adler
    0.14
    åijĺ
    0.14
     Wilkinson
    0.14
    ãĥ³ãĤ¯
    0.14
    if
    0.14
    Activations Density 0.006%

    No Known Activations