© 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. 19-LLAMASCOPE-RES-32K
    11. 4838
    Prev
    Next
    INDEX
    Explanations

    references to health-related products and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.15
    ·
    -0.14
    ³
    -0.14
    CESS
    -0.14
    ToBounds
    -0.13
    елен
    -0.13
    PHA
    -0.13
    oday
    -0.13
    edb
    -0.12
     Stake
    -0.12
    POSITIVE LOGITS
     treff
    0.15
    itler
    0.15
     anale
    0.14
    å»Ĭ
    0.13
    _flutter
    0.13
    abr
    0.13
    ¿
    0.13
     Mc
    0.13
    spender
    0.13
    άνι
    0.12
    Activations Density 0.767%

    No Known Activations