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. 1-LLAMASCOPE-RES-32K
    6. 28152
    Prev
    Next
    INDEX
    Explanations

    structured data representations or code-like syntax, particularly in the context of error handling and user policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equ
    -0.14
     ÙħÙĪØ±
    -0.14
    iversit
    -0.14
    eam
    -0.13
    (disposing
    -0.13
    åĨł
    -0.13
    rud
    -0.13
    аж
    -0.13
    ligne
    -0.13
    erte
    -0.13
    POSITIVE LOGITS
     Marshall
    0.16
     tank
    0.15
    marshall
    0.14
    288
    0.14
    zheimer
    0.14
    ndata
    0.14
    711
    0.14
     Linh
    0.14
    _marshall
    0.14
    ÃĸL
    0.14
    Activations Density 0.083%

    No Known Activations