© 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. 2-LLAMASCOPE-RES-32K
    11. 4798
    Prev
    Next
    INDEX
    Explanations

    terms associated with reckless or foolish behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enos
    -0.16
     ÙģÙĪ
    -0.15
    ampo
    -0.14
    _CIPHER
    -0.14
    uxe
    -0.14
    507
    -0.14
    UsageId
    -0.14
    .PLL
    -0.14
    .dw
    -0.14
     mdi
    -0.14
    POSITIVE LOGITS
    iker
    0.15
    162
    0.15
    163
    0.15
    /fast
    0.15
    simp
    0.15
    nes
    0.15
    acher
    0.14
    emes
    0.14
     care
    0.14
    andro
    0.14
    Activations Density 0.007%

    No Known Activations