© 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. 25-LLAMASCOPE-RES-32K
    11. 12024
    Prev
    Next
    INDEX
    Explanations

    information related to employee benefits and leave policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plier
    -0.16
    éłĨ
    -0.15
    ITO
    -0.15
    Fee
    -0.15
     Nom
    -0.15
    ampo
    -0.14
     Ingredient
    -0.14
    ¢åįķ
    -0.14
     Fee
    -0.14
     ingredient
    -0.14
    POSITIVE LOGITS
     leave
    0.55
     Leave
    0.47
    leave
    0.47
    Leave
    0.45
     leaves
    0.42
     sick
    0.41
    _leave
    0.39
     Sick
    0.38
     Leaves
    0.37
    .leave
    0.32
    Activations Density 0.051%

    No Known Activations