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. 25220
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "say" followed by various conjunctions or phrases

    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
     Dump
    -0.15
    aur
    -0.15
    pper
    -0.15
    ube
    -0.14
    .initializeApp
    -0.14
    λÏİ
    -0.14
    ciler
    -0.13
    ocio
    -0.13
    arty
    -0.13
    OKIE
    -0.13
    POSITIVE LOGITS
    314
    0.18
    urname
    0.17
    778
    0.15
    eh
    0.15
     Sext
    0.15
    asive
    0.14
    /banner
    0.14
     Sez
    0.14
    olulu
    0.14
    865
    0.13
    Activations Density 0.014%

    No Known Activations