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. 17-LLAMASCOPE-RES-32K
    6. 30549
    Prev
    Next
    INDEX
    Explanations

    mentions of the public figure Winfrey, particularly in a negative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ea
    -0.16
    yll
    -0.16
    een
    -0.16
    east
    -0.16
    INO
    -0.15
    оÑĦ
    -0.15
    ino
    -0.15
     Krish
    -0.14
    venge
    -0.14
    eron
    -0.14
    POSITIVE LOGITS
    ipeg
    0.24
    ograd
    0.19
    -win
    0.19
    nable
    0.18
    row
    0.18
    throp
    0.17
    nesota
    0.17
    now
    0.16
    ERRU
    0.16
    .UltraWin
    0.16
    Activations Density 0.025%

    No Known Activations