© 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. 30-LLAMASCOPE-RES-32K
    11. 22102
    Prev
    Next
    INDEX
    Explanations

    specific dates and locations for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     æĬķ稿æĹ¥
    -0.15
    åľ¨çº¿éĺħ读
    -0.13
     PMID
    -0.13
     пÑĢазд
    -0.13
    nex
    -0.13
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.13
    éĺħ读次æķ°
    -0.12
    ,'#
    -0.12
    دا
    -0.12
    ç½ijåĪĬ
    -0.12
    POSITIVE LOGITS
     |
    0.29
     âĢ¢
    0.26
     /
    0.25
     //
    0.25
     ||
    0.23
    ,↵
    0.23
     ·
    0.22
     -
    0.21
    *↵
    0.21
    ↵
    0.21
    Activations Density 1.222%

    No Known Activations