© 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. 23-LLAMASCOPE-RES-32K
    11. 12022
    Prev
    Next
    INDEX
    Explanations

    topics related to education and community engagement

    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
     Global
    -0.25
    Global
    -0.24
     Worlds
    -0.19
     World
    -0.19
     globalization
    -0.19
    _Global
    -0.18
    _global
    -0.18
     Globals
    -0.18
     International
    -0.18
    (Global
    -0.17
    POSITIVE LOGITS
     nationwide
    0.71
    åħ¨åĽ½
    0.56
     across
    0.46
     Nationwide
    0.45
     statewide
    0.45
     national
    0.44
     ìłĦêµŃ
    0.42
     nation
    0.41
     everywhere
    0.41
     Across
    0.40
    Activations Density 0.637%

    No Known Activations