© 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. 29-LLAMASCOPE-RES-32K
    6. 2339
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Red" in relation to the Red Sox or the context of baseball

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    婦
    -0.16
    apsed
    -0.15
    adier
    -0.15
    ruba
    -0.15
    }elseif
    -0.15
    opian
    -0.14
    ä½³
    -0.14
    odel
    -0.14
     Feinstein
    -0.14
    mekte
    -0.14
    POSITIVE LOGITS
     Stock
    0.30
     stock
    0.29
    stock
    0.25
    sock
    0.25
    Stock
    0.23
    birds
    0.23
    -stock
    0.22
     STOCK
    0.22
     Sox
    0.21
     stocks
    0.21
    Activations Density 0.006%

    No Known Activations