© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 19033
    Prev
    Next
    INDEX
    Explanations

    references to popular culture and contemporary figures

    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
    /WebAPI
    -0.15
    /gl
    -0.14
     preferredStyle
    -0.13
    gateway
    -0.13
    gpu
    -0.13
    μμ
    -0.12
    agu
    -0.12
    guard
    -0.12
    gesture
    -0.12
    /gen
    -0.12
    POSITIVE LOGITS
     G
    1.47
    G
    0.96
    ÂłG
    0.84
    =G
    0.83
    .G
    0.75
    >G
    0.69
    <G
    0.66
    ,G
    0.65
     Ðĵ
    0.63
    [G
    0.62
    Activations Density 0.788%

    No Known Activations