© 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. 11-LLAMASCOPE-RES-32K
    11. 7498
    Prev
    Next
    INDEX
    Explanations

    terms related to health and safety issues, with a focus on medical and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    μÏĢ
    -0.15
    isinde
    -0.15
    olib
    -0.14
     peri
    -0.14
    chter
    -0.14
    ãģ®äºº
    -0.13
    aternity
    -0.13
    ird
    -0.13
    kola
    -0.13
    ecer
    -0.13
    POSITIVE LOGITS
    utm
    0.17
    fal
    0.13
    зн
    0.13
    mey
    0.13
    aph
    0.13
     кеÑĢ
    0.13
    stown
    0.13
    earn
    0.13
    bee
    0.13
    lette
    0.13
    Activations Density 0.491%

    No Known Activations