© 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. 31-LLAMASCOPE-RES-32K
    11. 17436
    Prev
    Next
    INDEX
    Explanations

    phrases that critique superficial acts or performances, particularly in contexts of authenticity and sincerity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ragaz
    -0.15
     kariy
    -0.14
    \Lib
    -0.14
     dejting
    -0.14
     dejtingsaj
    -0.13
    nesc
    -0.13
    ixel
    -0.13
     dejtings
    -0.13
    #__
    -0.13
     annonces
    -0.12
    POSITIVE LOGITS
     fucking
    0.85
     Fucking
    0.71
     damn
    0.69
     fuck
    0.67
     damned
    0.66
     freaking
    0.65
     FUCK
    0.63
     bloody
    0.56
     god
    0.55
    damn
    0.55
    Activations Density 0.835%

    No Known Activations