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. 12-LLAMASCOPE-RES-32K
    6. 19643
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal declarations or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hey
    -0.18
    acre
    -0.17
    à¸ĩาà¸Ļ
    -0.16
    .CodeAnalysis
    -0.15
    nemonic
    -0.15
    aille
    -0.14
    peq
    -0.14
    asser
    -0.14
    Äħ
    -0.14
     nhau
    -0.14
    POSITIVE LOGITS
    /assert
    0.17
    (strict
    0.16
    LOUR
    0.16
    atively
    0.15
    idebar
    0.15
    ource
    0.15
    ̧
    0.15
    ounce
    0.14
    EditingStyle
    0.14
    ign
    0.14
    Activations Density 0.034%

    No Known Activations