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. 6-LLAMASCOPE-RES-32K
    6. 10369
    Prev
    Next
    INDEX
    Explanations

    occurrences of the ".org" domain in URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è£ķ
    -0.16
    rar
    -0.16
    oucher
    -0.16
    ики
    -0.16
    uchar
    -0.15
    iky
    -0.15
    ÑijÑĢ
    -0.15
    ondrous
    -0.14
    intColor
    -0.14
    sdale
    -0.14
    POSITIVE LOGITS
    abet
    0.17
    andler
    0.15
     #%
    0.15
     Fav
    0.15
    ill
    0.15
    ABEL
    0.14
    /twitter
    0.14
    IBC
    0.14
    aben
    0.14
    lernen
    0.14
    Activations Density 0.003%

    No Known Activations