© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    fondness and attachment

    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
    èĪĪ
    -0.09
    ertil
    -0.09
    .nlm
    -0.09
    çİĦ
    -0.09
    -bodied
    -0.09
     ì¶ķ
    -0.08
    orp
    -0.08
    ,ID
    -0.08
     Kiss
    -0.08
    _FW
    -0.08
    POSITIVE LOGITS
     fond
    0.32
     Fond
    0.26
     attachment
    0.24
     affection
    0.23
     attachments
    0.21
     bond
    0.20
     fon
    0.20
     attach
    0.19
     grew
    0.19
     attached
    0.19
    Activations Density 0.082%

    No Known Activations