© 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. 16339
    Prev
    Next
    INDEX
    Explanations

    motion or movement-related verbs and phrases

    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
    خت
    -0.14
    ventus
    -0.14
     upstream
    -0.14
    986
    -0.14
    Forward
    -0.13
     walkthrough
    -0.13
    ®¤
    -0.13
     Premi
    -0.13
    luv
    -0.13
     gone
    -0.13
    POSITIVE LOGITS
     across
    0.25
     throughout
    0.24
    sthrough
    0.20
     Across
    0.20
    Across
    0.19
     THROUGH
    0.18
     through
    0.17
     Throughout
    0.16
    nem
    0.15
    AAP
    0.15
    Activations Density 0.082%

    No Known Activations