© 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. 26-LLAMASCOPE-RES-32K
    11. 28572
    Prev
    Next
    INDEX
    Explanations

    details about vehicle accidents and their circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Machines
    -0.17
    ple
    -0.15
    .debian
    -0.14
    PLE
    -0.14
    izo
    -0.14
     machines
    -0.14
    sted
    -0.14
     padd
    -0.14
    ICO
    -0.14
     aviation
    -0.14
    POSITIVE LOGITS
     van
    0.22
     Pri
    0.22
     Nisan
    0.22
     Bu
    0.22
     Civic
    0.21
    Bu
    0.20
     sedan
    0.20
    Pri
    0.20
     Expedition
    0.20
     Ford
    0.19
    Activations Density 0.097%

    No Known Activations