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. 4-LLAMASCOPE-RES-32K
    6. 30925
    Prev
    Next
    INDEX
    Explanations

    phrases with the article "a" followed by various nouns and descriptors

    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
    exus
    -0.16
    oding
    -0.16
    643
    -0.16
    um
    -0.15
     Drink
    -0.14
    597
    -0.14
    indow
    -0.14
     Naj
    -0.14
    etwork
    -0.14
     Main
    -0.14
    POSITIVE LOGITS
    corner
    0.16
    ebek
    0.16
    acf
    0.15
    _compat
    0.15
    dma
    0.15
    uforia
    0.14
    ι
    0.14
     Wealth
    0.14
    acct
    0.14
    tres
    0.14
    Activations Density 0.015%

    No Known Activations