© 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. 23-LLAMASCOPE-RES-32K
    11. 21407
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly the presence of men and women 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 @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нÑĮ
    -0.15
    utan
    -0.15
    ollipop
    -0.15
    VIC
    -0.15
    oron
    -0.15
    lesi
    -0.14
    Male
    -0.14
    дÑĢом
    -0.14
    icina
    -0.14
    ritis
    -0.14
    POSITIVE LOGITS
     women
    0.59
     woman
    0.54
    women
    0.49
     Women
    0.43
    Women
    0.42
     WOM
    0.42
    女人
    0.41
    woman
    0.41
     Woman
    0.40
     mujeres
    0.38
    Activations Density 0.036%

    No Known Activations