© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42013
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun and then powers or abilities

    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
    ocale
    -0.10
     mas
    -0.09
     Achievement
    -0.09
    ilyn
    -0.09
    ------------\n
    -0.09
    loquent
    -0.08
    imestamp
    -0.08
    ivate
    -0.08
    resource
    -0.08
    uggage
    -0.08
    POSITIVE LOGITS
     powers
    0.55
    powers
    0.43
     Powers
    0.37
     abilities
    0.33
     ability
    0.27
    èĥ½åĬĽ
    0.24
    abilities
    0.23
     power
    0.23
    owers
    0.22
     gifts
    0.20
    Activations Density 0.109%

    No Known Activations