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. 15-LLAMASCOPE-RES-32K
    6. 25189
    Prev
    Next
    INDEX
    Explanations

    the concept of "difference" or variations across multiple contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اÙĨÙĩ
    -0.17
    ses
    -0.15
    hip
    -0.14
    roupe
    -0.14
    otes
    -0.14
    chest
    -0.14
    imet
    -0.14
    iliary
    -0.14
    ship
    -0.13
    969
    -0.13
    POSITIVE LOGITS
    iating
    0.37
    ially
    0.28
    iator
    0.27
    iability
    0.26
    iators
    0.25
    ials
    0.24
    iates
    0.24
    iale
    0.22
    iations
    0.21
     kinds
    0.21
    Activations Density 0.051%

    No Known Activations