© 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. 1-LLAMASCOPE-RES-32K
    11. 23540
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wit" and variations of it, indicating a focus on humor and cleverness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ût
    -0.19
    atori
    -0.14
    uder
    -0.14
    uzzi
    -0.14
    erah
    -0.14
     PUS
    -0.14
    utz
    -0.14
    anks
    -0.14
    ož
    -0.13
    994
    -0.13
    POSITIVE LOGITS
    æľĭ
    0.16
    @email
    0.15
     Harley
    0.14
    dio
    0.14
    окон
    0.14
     zku
    0.13
     Leban
    0.13
    .WebControls
    0.13
    "urls
    0.13
     Ze
    0.13
    Activations Density 0.015%

    No Known Activations