© 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. 61727
    Prev
    Next
    INDEX
    Explanations

    specific targeting and modification

    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
     uniqueness
    -0.10
     Specialty
    -0.09
    inality
    -0.09
    _UNIQUE
    -0.09
     eskort
    -0.09
     perso
    -0.09
    -many
    -0.08
    ẫ
    -0.08
    __/
    -0.08
     personalize
    -0.08
    POSITIVE LOGITS
     specific
    0.64
     individual
    0.58
     particular
    0.49
     Specific
    0.46
     конкÑĢеÑĤ
    0.42
     Individual
    0.41
    individual
    0.40
    specific
    0.39
     einzel
    0.39
    -specific
    0.39
    Activations Density 0.267%

    No Known Activations