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. 16-LLAMASCOPE-RES-32K
    6. 21831
    Prev
    Next
    INDEX
    Explanations

    geographic locations and their characteristics

    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
    orest
    -0.18
    GN
    -0.14
    ละ
    -0.14
    koa
    -0.14
    ippo
    -0.14
    æ±Ł
    -0.14
    nings
    -0.14
    ichen
    -0.14
    inning
    -0.14
    ouses
    -0.14
    POSITIVE LOGITS
     island
    0.40
     islands
    0.39
     Island
    0.36
     Islands
    0.34
     оÑģÑĤÑĢов
    0.29
    å³¶
    0.26
    å²Ľ
    0.25
    à¹Ģà¸ģาะ
    0.24
     جز
    0.24
     ìĦ¬
    0.24
    Activations Density 0.151%

    No Known Activations