© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 13-LLAMASCOPE-RES-32K
    11. 17392
    Prev
    Next
    INDEX
    Explanations

    numerical values related to health and medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏĬ
    -0.14
    kır
    -0.13
    773
    -0.13
    iete
    -0.13
    iens
    -0.13
    appa
    -0.13
    affe
    -0.13
    zing
    -0.13
    _N
    -0.13
    730
    -0.12
    POSITIVE LOGITS
    ä¼´
    0.15
    asan
    0.14
    uste
    0.14
     TYPO
    0.14
     Sanford
    0.14
    ople
    0.14
    atten
    0.14
    á»ĩu
    0.13
    ToObject
    0.13
    ulpt
    0.13
    Activations Density 0.063%

    No Known Activations