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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-LLAMASCOPE-RES-32K
    6. 7247
    Prev
    Next
    INDEX
    Explanations

    terms related to financial gains and profit metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /email
    -0.19
    awan
    -0.14
    kova
    -0.14
    eks
    -0.14
    unar
    -0.14
    orate
    -0.14
    ä½ı
    -0.14
    erk
    -0.14
    jÅ¡ÃŃ
    -0.14
    TERNAL
    -0.13
    POSITIVE LOGITS
    ably
    0.18
    rens
    0.16
    .getContentPane
    0.15
    .nih
    0.14
     Bookmark
    0.14
    çİĩ
    0.14
    ystack
    0.14
    oreach
    0.14
    HK
    0.14
    shire
    0.14
    Activations Density 0.027%

    No Known Activations