© 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. 20-LLAMASCOPE-RES-32K
    11. 24315
    Prev
    Next
    INDEX
    Explanations

    key phrases and trends that indicate analysis or evaluation of patterns and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allon
    -0.14
    _equiv
    -0.14
    IT
    -0.14
    dde
    -0.14
     architekt
    -0.13
     Reminder
    -0.13
    ter
    -0.13
     balancing
    -0.13
    ra
    -0.12
    lein
    -0.12
    POSITIVE LOGITS
     trend
    0.77
     trends
    0.76
     pattern
    0.75
     patterns
    0.71
    pattern
    0.67
     Patterns
    0.64
     Pattern
    0.63
    Pattern
    0.60
    patterns
    0.59
     Trend
    0.59
    Activations Density 0.267%

    No Known Activations