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. 31-LLAMASCOPE-RES-32K
    6. 10754
    Prev
    Next
    INDEX
    Explanations

    structured data and metadata in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dorf
    -0.13
    umann
    -0.13
     Maggie
    -0.13
     Maurice
    -0.12
    oÄŁ
    -0.12
    irma
    -0.12
    ÙħÙĪÙĦ
    -0.11
    omanip
    -0.11
    à¤Łà¤ķ
    -0.11
    ounc
    -0.11
    POSITIVE LOGITS
     Met
    1.24
    Met
    1.14
    met
    1.13
     MET
    1.13
     met
    1.04
    MET
    1.04
     Metropolitan
    0.99
    _met
    0.98
     meta
    0.97
     Meta
    0.97
    Activations Density 0.304%

    No Known Activations