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

    Neuronpedia

    APICircuit 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. 25-LLAMASCOPE-RES-32K
    6. 265
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to party planning and hosting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daily
    -0.17
    achu
    -0.15
     Breakfast
    -0.15
     Chap
    -0.15
     ÄĮer
    -0.15
    .codehaus
    -0.14
     Kunden
    -0.14
     cafes
    -0.14
    isia
    -0.14
     chap
    -0.14
    POSITIVE LOGITS
     guests
    0.39
    guest
    0.36
     party
    0.34
     Guests
    0.34
    Guest
    0.33
     hosting
    0.33
     guest
    0.32
    Hosting
    0.32
    party
    0.31
     Hosting
    0.31
    Activations Density 0.278%

    No Known Activations