© 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. 27-LLAMASCOPE-RES-32K
    6. 18698
    Prev
    Next
    INDEX
    Explanations

    references to legislative processes and voting outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /weather
    -0.16
     Chairman
    -0.15
    ilk
    -0.15
    hani
    -0.15
    hud
    -0.15
     supplement
    -0.14
    £i
    -0.14
     ent
    -0.14
    anik
    -0.14
     lawmaker
    -0.14
    POSITIVE LOGITS
     House
    0.37
    House
    0.32
     chamber
    0.29
     house
    0.28
     Chamber
    0.27
     HOUSE
    0.27
     upper
    0.24
     chambers
    0.24
     lower
    0.23
     Senate
    0.22
    Activations Density 0.054%

    No Known Activations