© 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. 20-LLAMASCOPE-RES-32K
    6. 11905
    Prev
    Next
    INDEX
    Explanations

    technical language related to engineering and operational effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aldi
    -0.14
    ãĥ«ãĥķ
    -0.14
    abez
    -0.13
    ÏĢη
    -0.13
    ught
    -0.13
    kle
    -0.13
    RM
    -0.13
     begun
    -0.13
     нее
    -0.13
    ummer
    -0.13
    POSITIVE LOGITS
     again
    0.22
    again
    0.20
     also
    0.20
    ate
    0.19
    also
    0.19
     respectively
    0.17
     Again
    0.15
    alus
    0.15
     ALSO
    0.15
    Again
    0.15
    Activations Density 0.370%

    No Known Activations