© 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. 25-LLAMASCOPE-RES-32K
    11. 18333
    Prev
    Next
    INDEX
    Explanations

    references to relationships and marital dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Husband
    -0.33
     boyfriend
    -0.32
     husbands
    -0.29
     husband
    -0.25
    ä¸Ī夫
    -0.24
     hubby
    -0.23
     мÑĥжÑĩин
    -0.22
     мÑĥж
    -0.20
     muž
    -0.19
    aida
    -0.19
    POSITIVE LOGITS
     wife
    0.80
     Wife
    0.67
    wife
    0.63
    -wife
    0.57
    妻
    0.56
     wives
    0.56
     esposa
    0.43
     vợ
    0.42
     vrouw
    0.38
    夫人
    0.37
    Activations Density 0.188%

    No Known Activations