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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-LLAMASCOPE-RES-32K
    6. 21495
    Prev
    Next
    INDEX
    Explanations

    expressions related to actions, conditions, and attributes that denote various degrees of need, obligation, and avoidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    моÑģ
    -0.15
    embro
    -0.14
    íĦ¸
    -0.13
    andr
    -0.13
     Zaman
    -0.12
    GenericType
    -0.12
    unger
    -0.12
    ä½įæĸ¼
    -0.12
    eds
    -0.12
    輪
    -0.11
    POSITIVE LOGITS
    odzi
    0.13
     Aleppo
    0.13
     intervening
    0.12
    "urls
    0.12
    ¤
    0.12
    (nullptr
    0.12
    //{{
    0.12
    ä¸ŃæĸĩåŃĹå¹ķ
    0.11
    @brief
    0.11
     záz
    0.11
    Activations Density 0.038%

    No Known Activations