© 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. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34632
    Prev
    Next
    INDEX
    Explanations

    possessive mother figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Daddy
    -0.18
     Papa
    -0.14
    çĪ·
    -0.13
     Girls
    -0.12
     daddy
    -0.12
     Fathers
    -0.12
    Girls
    -0.11
     ragazze
    -0.11
     Brother
    -0.11
    åŃĻ
    -0.10
    POSITIVE LOGITS
     mother
    0.48
    mother
    0.33
    æ¯į
    0.31
    æ¯į亲
    0.30
     Mother
    0.30
     mom
    0.30
     mothers
    0.29
     madre
    0.29
     mãe
    0.28
    Mother
    0.26
    Activations Density 0.102%

    No Known Activations