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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 21624
    Prev
    Next
    INDEX
    Explanations

    references to fines and penalties associated with legal or regulatory violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anki
    -0.16
    getBlock
    -0.16
    aus
    -0.14
     grat
    -0.14
     nieu
    -0.14
     Hedge
    -0.14
     artificially
    -0.14
     hed
    -0.14
     Eaton
    -0.13
     Artificial
    -0.13
    POSITIVE LOGITS
    ç½ļ
    0.21
     penalty
    0.19
     penalties
    0.19
     fined
    0.19
     fines
    0.18
    ovah
    0.18
    $MESS
    0.17
     phạt
    0.17
    ateg
    0.16
     fine
    0.16
    Activations Density 0.028%

    No Known Activations