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. 13-LLAMASCOPE-RES-32K
    6. 16586
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming and code commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -prepend
    -0.15
    éŀ
    -0.15
    .windows
    -0.15
    _strerror
    -0.14
    ounter
    -0.14
    gas
    -0.14
    721
    -0.14
     humor
    -0.14
    ä¾
    -0.14
     Palm
    -0.14
    POSITIVE LOGITS
    IBE
    0.15
    UY
    0.15
    åľŃ
    0.14
     spare
    0.14
    éļĽ
    0.14
    feld
    0.14
    356
    0.13
    abeth
    0.13
     Ãľst
    0.13
    oliberal
    0.13
    Activations Density 0.008%

    No Known Activations