© 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. 18-LLAMASCOPE-RES-32K
    11. 3114
    Prev
    Next
    INDEX
    Explanations

    discussions about smoking policies and associated health risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avar
    -0.16
    alim
    -0.15
    nemonic
    -0.15
     Scar
    -0.15
    ãģ¯ãģļ
    -0.15
    endon
    -0.14
    .tax
    -0.14
    aud
    -0.14
    adio
    -0.14
    æ¡
    -0.14
    POSITIVE LOGITS
     indoor
    0.16
     zones
    0.16
     pros
    0.15
    erged
    0.15
    bsite
    0.15
     workplaces
    0.14
    å¸ĥ
    0.14
     workplace
    0.14
     public
    0.14
     Indoor
    0.14
    Activations Density 0.044%

    No Known Activations