© 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. 6039
    Prev
    Next
    INDEX
    Explanations

    messages related to employee benefits and workplace engagement

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     oneself
    -0.19
    åıĬãģ³
    -0.17
     Whilst
    -0.16
     fucks
    -0.16
    Whilst
    -0.15
    亦
    -0.15
     Fucking
    -0.15
     whilst
    -0.15
     FUCK
    -0.15
     fucking
    -0.14
    POSITIVE LOGITS
     your
    0.18
    empo
    0.16
     yours
    0.15
    !*
    0.15
     âĨĵ
    0.14
    your
    0.14
    *
    0.14
     YOUR
    0.14
    ymb
    0.14
     just
    0.14
    Activations Density 0.623%

    No Known Activations