© 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. 11-LLAMASCOPE-RES-32K
    11. 17757
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding hypocrisy and its implications in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hood
    -0.15
    ben
    -0.14
     Daly
    -0.14
    СÐŀ
    -0.14
    ICAL
    -0.14
    vier
    -0.14
    DAQ
    -0.14
     Liv
    -0.14
    /Delete
    -0.14
    ical
    -0.13
    POSITIVE LOGITS
    mere
    0.20
     merely
    0.20
     mere
    0.19
     곧
    0.16
     ìķĦëĭĪëĿ¼
    0.14
     necessarily
    0.14
    _PHP
    0.14
     Bah
    0.14
     rocket
    0.14
    Ø«ÙĦ
    0.14
    Activations Density 0.213%

    No Known Activations