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. 6-LLAMASCOPE-RES-32K
    6. 7782
    Prev
    Next
    INDEX
    Explanations

    details related to legislative actions and nominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    202
    -0.19
     https
    -0.17
    æĤ
    -0.17
     novel
    -0.15
     MVP
    -0.15
    https
    -0.15
     Novel
    -0.15
    Telegram
    -0.15
     AI
    -0.14
     now
    -0.14
    POSITIVE LOGITS
     Wii
    0.16
    Obama
    0.16
     Obama
    0.16
    .googlecode
    0.15
    dzi
    0.15
     Boehner
    0.15
    зи
    0.15
    ahoo
    0.15
     Fukushima
    0.14
    ê·Ģ
    0.14
    Activations Density 0.385%

    No Known Activations