© 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. 23430
    Prev
    Next
    INDEX
    Explanations

    effect/affect

    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
     Kear
    -0.10
    avanaugh
    -0.09
     persuaded
    -0.09
     Haven
    -0.09
    Been
    -0.08
     screwed
    -0.08
    avad
    -0.08
    леж
    -0.08
    tml
    -0.08
     rebel
    -0.08
    POSITIVE LOGITS
     effect
    0.25
     Effect
    0.21
    Effect
    0.18
    effect
    0.17
    æķĪæŀľ
    0.17
     affect
    0.17
    -effect
    0.16
     EFFECT
    0.16
     effects
    0.16
     efect
    0.16
    Activations Density 0.035%

    No Known Activations