© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 4781
    Prev
    Next
    INDEX
    Explanations

    mentions of bicycles and cycling-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bulld
    -0.16
     Cabinet
    -0.15
     scrim
    -0.14
    odka
    -0.14
     Diesel
    -0.14
     diving
    -0.14
    acz
    -0.14
     Bulld
    -0.13
    LP
    -0.13
    bul
    -0.13
    POSITIVE LOGITS
     bike
    0.46
     Bike
    0.45
     bikes
    0.42
    bike
    0.41
     Bicycle
    0.40
     pedals
    0.40
     riders
    0.40
     Cycling
    0.40
     bicycle
    0.39
     cyclists
    0.39
    Activations Density 0.364%

    No Known Activations