© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 15790
    Prev
    Next
    INDEX
    Explanations

    mentions of U.S. senators, especially in the context of legislative activities or affiliations

    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
    bus
    -0.17
    _transfer
    -0.16
    Speaker
    -0.16
     Speaker
    -0.15
     bron
    -0.15
    fuse
    -0.15
    PerPixel
    -0.14
    sticky
    -0.14
     congressman
    -0.14
     house
    -0.14
    POSITIVE LOGITS
     Senate
    0.38
     senators
    0.37
     senator
    0.36
     Sen
    0.35
     Senators
    0.35
     Senator
    0.34
    Sen
    0.34
     senate
    0.34
     SEN
    0.29
    Senate
    0.29
    Activations Density 0.143%

    No Known Activations