© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 5659
    Prev
    Next
    INDEX
    Explanations

    terms related to health benefits and therapeutic effects of natural ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rior
    -0.15
    tuÄŁ
    -0.15
    912
    -0.15
     Ridley
    -0.14
    .TestTools
    -0.14
    .spacing
    -0.14
    _ONCE
    -0.14
    ucid
    -0.14
    nero
    -0.14
     datum
    -0.14
    POSITIVE LOGITS
     LDL
    0.24
     inflammation
    0.22
     harmful
    0.20
     oxidative
    0.20
     signs
    0.20
     bad
    0.19
     infl
    0.19
     free
    0.19
     damaging
    0.18
     inflamm
    0.18
    Activations Density 0.099%

    No Known Activations