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. 7-LLAMASCOPE-RES-32K
    6. 13665
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data processing and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    905
    -0.15
    icons
    -0.14
    incy
    -0.14
     cáºŃn
    -0.14
     ins
    -0.14
    Ø·Ùģ
    -0.14
    estre
    -0.13
    ataka
    -0.13
    æķı
    -0.13
    inqu
    -0.13
    POSITIVE LOGITS
     Doc
    0.16
    doc
    0.15
    ois
    0.14
    oui
    0.14
    Doc
    0.14
    ystack
    0.14
     doc
    0.14
     SND
    0.14
    pon
    0.14
    .getObject
    0.14
    Activations Density 0.003%

    No Known Activations