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. 15-LLAMASCOPE-RES-32K
    6. 9349
    Prev
    Next
    INDEX
    Explanations

    aspects related to the driving experience of hybrid vehicles

    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
     sư
    -0.16
     Manning
    -0.15
     Babe
    -0.15
    μμ
    -0.14
    itel
    -0.14
     Lois
    -0.14
     Barcl
    -0.13
    .getColumnIndex
    -0.13
    éĿ
    -0.13
    ÑģÑĤоÑĢ
    -0.13
    POSITIVE LOGITS
    warts
    0.17
     deb
    0.17
    lemn
    0.16
    amo
    0.16
     instrument
    0.16
     segment
    0.15
     instruments
    0.14
    -pill
    0.14
     spoilers
    0.14
     le
    0.14
    Activations Density 0.239%

    No Known Activations