© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 15937
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angi
    -0.15
    ads
    -0.15
     West
    -0.14
     Bart
    -0.14
    erts
    -0.14
    Į
    -0.14
    VR
    -0.14
    uid
    -0.14
     cater
    -0.14
     Last
    -0.14
    POSITIVE LOGITS
     sole
    0.20
    alone
    0.19
    _UNIQUE
    0.18
     responsibility
    0.16
     Responsibility
    0.16
     alone
    0.16
    ä½
    0.15
    çį¨
    0.15
    çĭ¬
    0.14
    -alone
    0.14
    Activations Density 0.035%

    No Known Activations