© 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. 29-LLAMASCOPE-RES-32K
    6. 3907
    Prev
    Next
    INDEX
    Explanations

    phrases focused on pet care, particularly regarding dog ownership and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unsch
    -0.15
     Butterfly
    -0.14
    /perl
    -0.14
    eldon
    -0.13
    undler
    -0.13
     nackte
    -0.13
     Sesso
    -0.13
    аÑĢÑĩ
    -0.13
     Verfüg
    -0.13
    remen
    -0.13
    POSITIVE LOGITS
     dog
    0.81
     dogs
    0.75
     Dog
    0.74
    dog
    0.71
    Dog
    0.69
     Dogs
    0.67
     canine
    0.62
    dogs
    0.61
     pet
    0.57
     pets
    0.53
    Activations Density 0.772%

    No Known Activations