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. 8-LLAMASCOPE-RES-32K
    6. 22680
    Prev
    Next
    INDEX
    Explanations

    words related to errors and error handling in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    en
    -0.18
     flexGrow
    -0.15
    enk
    -0.15
    زÙĦ
    -0.15
     pol
    -0.15
     Ham
    -0.14
    /Users
    -0.14
    äch
    -0.14
    erus
    -0.14
     fle
    -0.14
    POSITIVE LOGITS
    ormsg
    0.16
    _amp
    0.15
    udoku
    0.14
    ForResource
    0.14
    pcm
    0.14
    ợ
    0.14
    GetPosition
    0.14
    =nil
    0.14
    bage
    0.14
    oplevel
    0.14
    Activations Density 0.004%

    No Known Activations