© 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. 17-LLAMASCOPE-RES-32K
    11. 27775
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to industry knowledge and events in the insurance sector

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bowman
    -0.17
    538
    -0.15
    669
    -0.15
    incer
    -0.14
     loc
    -0.14
    coon
    -0.14
     bil
    -0.14
     para
    -0.14
    ooth
    -0.14
     tý
    -0.14
    POSITIVE LOGITS
     industry
    0.20
    industry
    0.18
     Industry
    0.16
    Industry
    0.15
    ãĥĨãĥ«
    0.15
     Sesso
    0.15
    irket
    0.14
    è¡Įä¸ļ
    0.14
    ukkan
    0.14
     صÙĨعت
    0.14
    Activations Density 0.127%

    No Known Activations