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. 29-LLAMASCOPE-RES-32K
    6. 12468
    Prev
    Next
    INDEX
    Explanations

    expressions of celebration and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _WIDGET
    -0.15
     Mondays
    -0.14
     Saturdays
    -0.14
     Fridays
    -0.14
     dbo
    -0.13
    htag
    -0.13
     Kardash
    -0.13
     ÄĮech
    -0.13
    oles
    -0.13
     Tues
    -0.13
    POSITIVE LOGITS
     Labor
    0.44
     Memorial
    0.40
     Mother
    0.39
     Independence
    0.39
     Father
    0.38
     Labour
    0.35
    Independ
    0.32
     Mothers
    0.32
    Mother
    0.31
    Labor
    0.30
    Activations Density 0.699%

    No Known Activations