© 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. 9-LLAMASCOPE-RES-32K
    11. 4508
    Prev
    Next
    INDEX
    Explanations

    references to female characters and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himself
    -0.29
    妻
    -0.25
     stesso
    -0.21
    /she
    -0.19
     Himself
    -0.19
    sing
    -0.18
    his
    -0.18
     ÙĨÙģسÙĩ
    -0.18
     Jr
    -0.18
    ä¿Ĭ
    -0.18
    POSITIVE LOGITS
     herself
    0.54
     могла
    0.25
     Ñģама
    0.24
    athed
    0.22
     должна
    0.22
    ä¸Ī夫
    0.21
     ÑģÑĤала
    0.20
    ová
    0.20
    /he
    0.19
     Ñģказала
    0.19
    Activations Density 3.716%

    No Known Activations