Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 8076
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and mentions of popular foods

    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
     ëĭ¤ìļ´ë°Ľê¸°
    -0.13
    ëį°ìĿ´íĬ¸
    -0.13
    EIF
    -0.13
    registro
    -0.13
    serrat
    -0.12
    detalle
    -0.12
    andex
    -0.12
    (íģ¬ê¸°
    -0.12
     ведÑĮ
    -0.12
    È
    -0.12
    POSITIVE LOGITS
    â̦↵
    0.14
       
    0.14
    â̦↵↵
    0.13
    â̦I
    0.13
    â̦”
    0.13
    âĢı
    0.13
     meiden
    0.13
    ÃŃrk
    0.12
     nouve
    0.12
    â̦the
    0.12
    Activations Density 2.141%

    No Known Activations