© 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. 31-LLAMASCOPE-RES-32K
    11. 20378
    Prev
    Next
    INDEX
    Explanations

    details about product launches and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kosovo
    -0.17
     Appalachian
    -0.17
     Klopp
    -0.17
    åĿª
    -0.17
     Bengals
    -0.17
    jos
    -0.17
     Cuban
    -0.16
     Lennon
    -0.16
     Atlanta
    -0.16
    Atlanta
    -0.16
    POSITIVE LOGITS
     Xperia
    0.58
     Sony
    0.50
    Sony
    0.43
     PlayStation
    0.29
    peria
    0.25
     Playstation
    0.25
     SCE
    0.24
     Sonia
    0.23
    ONY
    0.22
    ony
    0.22
    Activations Density 0.013%

    No Known Activations