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. 3-LLAMASCOPE-RES-32K
    6. 23785
    Prev
    Next
    INDEX
    Explanations

    references to the "System" namespace in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apore
    -0.17
    itorio
    -0.16
    tright
    -0.15
    indre
    -0.15
    istros
    -0.14
    atable
    -0.14
    uffman
    -0.14
    zyst
    -0.14
    odem
    -0.14
    orable
    -0.14
    POSITIVE LOGITS
     Christie
    0.15
     Sith
    0.15
    fol
    0.14
    _nth
    0.14
    Desk
    0.14
    вед
    0.14
    _fold
    0.14
    .lon
    0.13
     Fold
    0.13
    estr
    0.13
    Activations Density 0.001%

    No Known Activations