© 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. 7052
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to complex systems

    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
    mage
    -0.16
    aurus
    -0.15
     Hath
    -0.15
    adle
    -0.15
    CTest
    -0.14
    cia
    -0.14
    ubbo
    -0.14
    /goto
    -0.14
     kap
    -0.14
    ItemAt
    -0.14
    POSITIVE LOGITS
    ais
    0.16
    lad
    0.15
    ADA
    0.14
    ç½²
    0.14
    Explicit
    0.14
    车
    0.14
    è»Ĭ
    0.14
    836
    0.13
    ãĥ¼ãĥĨ
    0.13
    ardin
    0.13
    Activations Density 0.158%

    No Known Activations