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. 682
    Prev
    Next
    INDEX
    Explanations

    instances of error handling and debugging statements in code

    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
     McCart
    -0.15
    ember
    -0.14
    innie
    -0.14
     amp
    -0.13
    ackers
    -0.13
    amin
    -0.13
    etype
    -0.13
     Jac
    -0.13
     nearly
    -0.13
    ÃŃa
    -0.13
    POSITIVE LOGITS
    rypton
    0.16
    iversit
    0.16
    onis
    0.15
    ADIO
    0.14
    ìĦ¼
    0.14
    shal
    0.14
    ãĥ³ãĤ°
    0.14
     Rolls
    0.14
    ilha
    0.14
    ácil
    0.13
    Activations Density 0.003%

    No Known Activations