© 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. 30-LLAMASCOPE-RES-32K
    11. 9165
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to database operations and optimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tongues
    -0.16
     ëĦ¤ìĿ´íĬ¸
    -0.15
     newspapers
    -0.14
     Catch
    -0.14
    Catch
    -0.14
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    -0.14
    å¯
    -0.13
    _mock
    -0.13
    :variables
    -0.13
     Pay
    -0.13
    POSITIVE LOGITS
     operations
    0.31
     calls
    0.27
     operation
    0.26
    operations
    0.25
     requests
    0.25
     writes
    0.23
    operation
    0.22
     interactions
    0.22
     commands
    0.22
     computations
    0.22
    Activations Density 0.254%

    No Known Activations