© 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 EvalsExportsAPI 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. 16033
    Prev
    Next
    INDEX
    Explanations

    coding and programming constructs, especially those related to data handling and manipulations

    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
     method
    -0.20
     Info
    -0.19
     Tech
    -0.18
     Prod
    -0.18
     goal
    -0.18
     creation
    -0.18
     Init
    -0.18
     Proc
    -0.17
    _buf
    -0.17
     action
    -0.17
    POSITIVE LOGITS
    _typeDefinition
    0.22
    _maximum
    0.19
    _configuration
    0.19
    _parameter
    0.17
    _information
    0.17
    _structure
    0.17
    _frequency
    0.16
    _expression
    0.16
    _function
    0.16
    _probability
    0.16
    Activations Density 0.051%

    No Known Activations