© 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. 22-LLAMASCOPE-RES-32K
    11. 10753
    Prev
    Next
    INDEX
    Explanations

    legal terms related to business formation and agreements

    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
    ythe
    -0.19
    vrier
    -0.18
    evi
    -0.14
    ISA
    -0.14
     каб
    -0.14
    itbart
    -0.13
    geois
    -0.13
    bou
    -0.13
     Äijảo
    -0.13
    isque
    -0.13
    POSITIVE LOGITS
    formation
    0.25
     formation
    0.24
     Formation
    0.23
    Formation
    0.22
     dissolution
    0.22
     formations
    0.20
     Articles
    0.19
     incorpor
    0.19
     Diss
    0.19
     articles
    0.19
    Activations Density 0.013%

    No Known Activations