© 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. 31-LLAMASCOPE-RES-32K
    11. 2620
    Prev
    Next
    INDEX
    Explanations

    details related to legal agreements and the validity of offers in lawsuits

    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
    ummings
    -0.16
    roperties
    -0.16
    .responses
    -0.16
    ittest
    -0.15
     arada
    -0.15
    ersist
    -0.14
    uteur
    -0.14
    unte
    -0.14
    ahat
    -0.14
     duo
    -0.14
    POSITIVE LOGITS
     finding
    0.34
     determination
    0.26
     Finding
    0.26
    finding
    0.25
     written
    0.23
     claim
    0.22
     right
    0.22
    Finding
    0.21
     showing
    0.20
     proceeding
    0.20
    Activations Density 0.262%

    No Known Activations