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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 1-LLAMASCOPE-RES-32K
    11. 28900
    Prev
    Next
    INDEX
    Explanations

    instances of the word "falling" and related terms indicating descent or failure

    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
    rin
    -0.17
    alon
    -0.14
     Windsor
    -0.14
     Twice
    -0.14
    resolver
    -0.13
     sess
    -0.13
    Hub
    -0.13
    IDD
    -0.13
    476
    -0.13
     Bes
    -0.13
    POSITIVE LOGITS
    oop
    0.16
    ëĮ
    0.14
    :"-"`↵
    0.14
    ìĿ´íĬ¸
    0.14
     vig
    0.14
    ibold
    0.14
    reen
    0.14
    Forgery
    0.14
    adge
    0.14
     ï¿£
    0.14
    Activations Density 0.004%

    No Known Activations