© 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. 30-LLAMASCOPE-RES-32K
    11. 11746
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to managing body weight and fat, particularly "love handles."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hover
    -0.14
    acos
    -0.14
     Hover
    -0.13
    coni
    -0.13
    ChangedEventArgs
    -0.13
    лиÑĤ
    -0.13
     hyp
    -0.13
     Hyp
    -0.13
    HOOK
    -0.13
    ierce
    -0.13
    POSITIVE LOGITS
     handle
    1.01
     handles
    0.93
     handler
    0.93
     handling
    0.92
    handle
    0.88
     Handle
    0.88
     handlers
    0.86
     handled
    0.85
    -handle
    0.84
    .handle
    0.81
    Activations Density 0.211%

    No Known Activations