© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27172
    Prev
    Next
    INDEX
    Explanations

    mentions of notable events and their impacts within a historical context

    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
    uci
    -0.16
    ingleton
    -0.15
    685
    -0.15
     pul
    -0.14
    -0.14
     separ
    -0.13
     wings
    -0.13
     Trends
    -0.13
    odom
    -0.13
    venes
    -0.13
    POSITIVE LOGITS
     weather
    0.62
    weather
    0.50
     Weather
    0.47
    Weather
    0.42
    /weather
    0.40
     temperatures
    0.39
     rain
    0.38
    .weather
    0.36
    _weather
    0.36
     погод
    0.35
    Activations Density 0.551%

    No Known Activations