© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    references to events or announcements concerning releases or significant dates

    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
     weekend
    -0.34
    Saturday
    -0.33
     Saturday
    -0.32
     weekends
    -0.30
     Weekend
    -0.28
     Friday
    -0.26
     Saturdays
    -0.25
    Friday
    -0.24
     friday
    -0.23
    aturday
    -0.21
    POSITIVE LOGITS
    Tuesday
    0.23
     Tuesday
    0.23
     Tue
    0.22
     Tues
    0.20
    Tue
    0.18
     Monday
    0.17
    Monday
    0.17
     filament
    0.16
     monday
    0.15
     Mondays
    0.15
    Activations Density 0.069%

    No Known Activations