© 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. 23-LLAMASCOPE-RES-32K
    11. 1259
    Prev
    Next
    INDEX
    Explanations

    references to aviation incidents and related casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndexChanged
    -0.16
    Preview
    -0.15
    idl
    -0.15
     авÑĤомоб
    -0.15
    flo
    -0.14
    uni
    -0.14
    phinx
    -0.14
     bon
    -0.14
    stå
    -0.14
     car
    -0.14
    POSITIVE LOGITS
     Flight
    0.31
     crash
    0.29
    Flight
    0.28
     flight
    0.28
     cockpit
    0.25
     crashes
    0.24
     passenger
    0.23
     crashed
    0.23
     Boeing
    0.23
     plane
    0.23
    Activations Density 0.016%

    No Known Activations