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. 31-LLAMASCOPE-RES-32K
    6. 31152
    Prev
    Next
    INDEX
    Explanations

    phrases related to making choices and the concept of "the right thing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardless
    -0.14
    нова
    -0.13
    uck
    -0.13
    лава
    -0.13
    zcze
    -0.13
    Ñij
    -0.13
    roads
    -0.12
    ÑħÑĸд
    -0.12
    çͳåįļ
    -0.12
     zby
    -0.12
    POSITIVE LOGITS
     right
    0.97
    right
    0.77
     correct
    0.73
     RIGHT
    0.73
     Right
    0.71
    -right
    0.70
    Right
    0.67
    _right
    0.65
    .right
    0.63
    RIGHT
    0.62
    Activations Density 0.218%

    No Known Activations