© 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. 5115
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming, operations, and data processing

    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
    ÑĢиз
    -0.14
    uddy
    -0.12
    ekk
    -0.11
     κοι
    -0.11
    ÄįenÃŃ
    -0.11
    ราà¸Ħ
    -0.11
    иÑī
    -0.11
    svp
    -0.11
    uddle
    -0.10
    äl
    -0.10
    POSITIVE LOGITS
     oper
    1.05
     Oper
    0.98
     OPER
    0.98
     opera
    0.98
     operation
    0.98
    oper
    0.93
    -oper
    0.92
    OPER
    0.90
     опеÑĢ
    0.88
    Oper
    0.88
    Activations Density 0.176%

    No Known Activations