© 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. 27591
    Prev
    Next
    INDEX
    Explanations

    references to celebrity culture and public figures

    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
    pta
    -0.15
    \OptionsResolver
    -0.15
    igans
    -0.14
    ntag
    -0.14
     independents
    -0.14
     NÄĽm
    -0.14
    arbeit
    -0.14
    izu
    -0.14
    aise
    -0.14
    iap
    -0.13
    POSITIVE LOGITS
     celebrities
    0.40
     celebrity
    0.39
     cele
    0.36
     stars
    0.35
     star
    0.30
    stars
    0.28
     famous
    0.27
    cele
    0.27
    -ce
    0.26
     superstar
    0.26
    Activations Density 0.210%

    No Known Activations