© 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. 21-LLAMASCOPE-RES-32K
    11. 10003
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax related to programming logic and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.26
    ê±°ëŀĺê°Ģ
    -0.19
    ëį°ìĿ´íĬ¸
    -0.18
    ëĶĶìĭľ
    -0.17
     @}
    -0.17
    надлеж
    -0.17
    turnstile
    -0.17
     mbox
    -0.15
    ë³´ì¦Ŀê¸Ī
    -0.15
    ίθ
    -0.15
    POSITIVE LOGITS
     flush
    0.15
     blink
    0.15
     null
    0.14
     Constants
    0.14
     {↵
    0.14
    ´
    0.13
    284
    0.13
    0.13
    set
    0.13
    get
    0.13
    Activations Density 0.151%

    No Known Activations