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. 13-LLAMASCOPE-RES-32K
    6. 16524
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references related to historical events

    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
     Garrett
    -0.16
    ihil
    -0.15
    ipar
    -0.14
    rick
    -0.14
     unserialize
    -0.14
     Malk
    -0.14
    okud
    -0.14
     Gaul
    -0.14
    opsy
    -0.13
    _completion
    -0.13
    POSITIVE LOGITS
     alike
    0.26
     respectively
    0.20
    assen
    0.14
    oud
    0.14
    825
    0.13
     combo
    0.13
    reh
    0.13
     chapters
    0.13
     Licensed
    0.13
    ensive
    0.13
    Activations Density 0.029%

    No Known Activations