Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-LLAMASCOPE-RES-32K
    6. 23429
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Indianapolis and its associated events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atto
    -0.15
    ãĢħ
    -0.14
    [js
    -0.14
     Blond
    -0.13
    ic
    -0.13
    tryside
    -0.13
    ja
    -0.13
     Jar
    -0.13
    iq
    -0.13
     Kaf
    -0.13
    POSITIVE LOGITS
    ÙĪÙĩ
    0.15
    rieg
    0.15
    rand
    0.15
     onLoad
    0.14
    dar
    0.14
     Hancock
    0.14
    :\/\/
    0.14
    shire
    0.14
    رÙĩ
    0.14
    illac
    0.14
    Activations Density 0.003%

    No Known Activations