© 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. 13-LLAMASCOPE-RES-32K
    11. 14864
    Prev
    Next
    INDEX
    Explanations

    phrases related to political hypocrisy and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eker
    -0.15
    ë´ī
    -0.15
     Kurum
    -0.15
    eyim
    -0.14
    kám
    -0.14
    ảng
    -0.14
    ucket
    -0.13
    ombat
    -0.13
    odzi
    -0.13
     calculator
    -0.13
    POSITIVE LOGITS
     è²
    0.17
     when
    0.16
    ź
    0.15
    when
    0.15
    ewe
    0.15
     elephant
    0.14
    ULA
    0.14
     critical
    0.14
     Spi
    0.14
    ita
    0.14
    Activations Density 0.154%

    No Known Activations