© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 6-LLAMASCOPE-RES-32K
    11. 7601
    Prev
    Next
    INDEX
    Explanations

    Python programming concepts and syntax related to data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¹Ħà¸Ĥ
    -0.14
    Bon
    -0.14
     edition
    -0.14
     kara
    -0.13
    bart
    -0.13
    ve
    -0.13
    #index
    -0.13
     Büyük
    -0.13
     Bon
    -0.13
    .health
    -0.13
    POSITIVE LOGITS
    á»IJ
    0.15
    лав
    0.14
     Silence
    0.14
     pall
    0.13
    輪
    0.13
    λει
    0.13
    yas
    0.13
    .MenuItem
    0.12
     Brewer
    0.12
    ÙĬÙħÙĬ
    0.12
    Activations Density 0.225%

    No Known Activations