© 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. 31-LLAMASCOPE-RES-32K
    11. 9599
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly focusing on male identities and issues related to masculinity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guys
    -0.23
     Guys
    -0.21
     boys
    -0.19
     men
    -0.19
    ners
    -0.18
     Boys
    -0.17
    edly
    -0.15
    rei
    -0.15
     guy
    -0.15
     hombres
    -0.15
    POSITIVE LOGITS
    volent
    0.45
    -dominated
    0.36
    fic
    0.33
    /f
    0.28
    factor
    0.28
    -bodied
    0.28
    -only
    0.28
    -centric
    0.26
    -led
    0.26
    vol
    0.25
    Activations Density 0.021%

    No Known Activations