© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 12261
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, particularly those involving object methods and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uilder
    -0.17
    ocy
    -0.15
    uters
    -0.15
    lew
    -0.15
     chiá»ģu
    -0.15
    kovi
    -0.15
    rico
    -0.14
    леннÑĭй
    -0.14
    utow
    -0.14
    rlen
    -0.14
    POSITIVE LOGITS
     instanceof
    0.45
     isinstance
    0.31
    .GetType
    0.28
    .getClass
    0.28
     typeof
    0.28
    (isinstance
    0.27
     isKindOfClass
    0.26
    instance
    0.26
     isa
    0.26
     instance
    0.25
    Activations Density 0.060%

    No Known Activations