© 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. 22-LLAMASCOPE-RES-32K
    6. 11816
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" and related phrases indicating connections or additions between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nails
    -0.25
     nose
    -0.23
     needle
    -0.22
     noodles
    -0.22
     nitrogen
    -0.22
     nigeria
    -0.21
     nurses
    -0.21
     needles
    -0.21
     nail
    -0.21
     Nurses
    -0.21
    POSITIVE LOGITS
    Surname
    0.16
     gross
    0.15
    à¸ģรรม
    0.15
    ·»
    0.14
    ILINE
    0.14
    538
    0.13
    	throws
    0.13
     sur
    0.13
     m
    0.13
     din
    0.13
    Activations Density 0.152%

    No Known Activations