© 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. 31-LLAMASCOPE-RES-32K
    6. 9117
    Prev
    Next
    INDEX
    Explanations

    references to tickets, passes, and validation or invalidation of fare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     khắc
    -0.15
    _TestCase
    -0.14
    -mort
    -0.14
    getTable
    -0.13
    èĥİ
    -0.12
     polož
    -0.12
     greed
    -0.12
    FileSync
    -0.12
    Wake
    -0.12
    .lab
    -0.12
    POSITIVE LOGITS
     fare
    0.34
     fares
    0.30
     validity
    0.28
     Fare
    0.28
     card
    0.28
     ticket
    0.27
     validators
    0.27
     cards
    0.26
     validation
    0.26
     tickets
    0.26
    Activations Density 0.030%

    No Known Activations