© 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. 58995
    Prev
    Next
    INDEX
    Explanations

    lack of ability

    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
     correctness
    -0.10
    zes
    -0.10
    aeda
    -0.09
    vette
    -0.09
    orna
    -0.08
    thew
    -0.08
    riba
    -0.08
    çĶĺ
    -0.08
     Commentary
    -0.08
     mans
    -0.08
    POSITIVE LOGITS
     ability
    0.39
     capability
    0.29
     Ability
    0.23
    èĥ½åĬĽ
    0.23
     capacity
    0.21
    Ability
    0.21
    ability
    0.21
     option
    0.19
    capability
    0.19
     luxury
    0.19
    Activations Density 0.025%

    No Known Activations