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

    Neuronpedia

    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. 26-LLAMASCOPE-RES-32K
    11. 5689
    Prev
    Next
    INDEX
    Explanations

    terms related to medical warnings and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Silva
    -0.17
     Duck
    -0.16
    asha
    -0.15
    itta
    -0.15
     Gap
    -0.14
    idas
    -0.14
     annex
    -0.14
    inho
    -0.14
     regul
    -0.13
    atica
    -0.13
    POSITIVE LOGITS
     WARN
    0.18
    kaar
    0.16
    enda
    0.16
    Monitor
    0.16
    WARN
    0.16
    _FULLSCREEN
    0.16
    erialize
    0.16
    zier
    0.15
     boxed
    0.15
     CONTR
    0.15
    Activations Density 0.019%

    No Known Activations