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. 16-LLAMASCOPE-RES-32K
    6. 6184
    Prev
    Next
    INDEX
    Explanations

    Java import statements and class definitions related to web services and adapters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isle
    -0.17
    rades
    -0.16
    readystatechange
    -0.15
    alam
    -0.15
    arena
    -0.15
    kaar
    -0.14
    fet
    -0.14
    lear
    -0.14
    .itemView
    -0.14
    ê
    -0.14
    POSITIVE LOGITS
    »
    0.16
    ett
    0.15
    ahlen
    0.14
    inish
    0.14
    arti
    0.14
    ubi
    0.14
    éĺ´
    0.13
    ÑĢол
    0.13
    RootElement
    0.13
    athy
    0.13
    Activations Density 0.088%

    No Known Activations