© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 14-LLAMASCOPE-RES-32K
    11. 7464
    Prev
    Next
    INDEX
    Explanations

    times of day and references to evening or night

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breakfast
    -0.17
     Morning
    -0.17
     breakfast
    -0.17
    íķij
    -0.16
    ungan
    -0.16
     noon
    -0.15
    zeich
    -0.15
    mons
    -0.15
    oor
    -0.15
    ãĤ¢ãĥ¼
    -0.15
    POSITIVE LOGITS
     night
    0.27
    -night
    0.26
     nights
    0.26
     evening
    0.25
     tonight
    0.24
     evenings
    0.23
     nightly
    0.23
    æĻļ
    0.23
     Tonight
    0.23
    night
    0.21
    Activations Density 0.118%

    No Known Activations