© 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. 5753
    Prev
    Next
    INDEX
    Explanations

    terms related to working conditions and labor issues

    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
    /remove
    -0.34
    ings
    -0.30
    /write
    -0.25
    /disable
    -0.24
    /delete
    -0.24
    ify
    -0.23
    /close
    -0.22
    /change
    -0.20
    able
    -0.20
    ÂŃing
    -0.20
    POSITIVE LOGITS
    redients
    0.36
    /loading
    0.34
    ly
    0.34
    redient
    0.33
    /testing
    0.31
    ton
    0.30
    ness
    0.29
    enuity
    0.28
    -edge
    0.27
    /logging
    0.26
    Activations Density 1.704%

    No Known Activations