© 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. 15-LLAMASCOPE-RES-32K
    11. 23588
    Prev
    Next
    INDEX
    Explanations

    references to video games and related cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uilt
    -0.17
     Soon
    -0.15
    λÏİ
    -0.15
    ihar
    -0.14
    ÑĦеÑĢен
    -0.14
     soon
    -0.14
    isay
    -0.14
    raman
    -0.14
    utsche
    -0.14
    anges
    -0.13
    POSITIVE LOGITS
     modern
    0.76
    modern
    0.65
     contemporary
    0.62
     moderne
    0.61
     Modern
    0.60
     ÑģовÑĢем
    0.58
    Modern
    0.57
    çݰ代
    0.55
     ÑģÑĥÑĩаÑģ
    0.52
     Contemporary
    0.48
    Activations Density 0.504%

    No Known Activations