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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38591
    Prev
    Next
    INDEX
    Explanations

    faced stiff opposition

    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
    éĿ
    -0.10
    alus
    -0.10
    าà¸Ĭ
    -0.10
     Butter
    -0.10
    ｯ
    -0.09
    ê¹
    -0.09
     unstoppable
    -0.09
     ir
    -0.09
    Multiplicity
    -0.09
    ensitive
    -0.09
    POSITIVE LOGITS
     fight
    0.30
     Fight
    0.23
     fights
    0.23
     val
    0.23
     fought
    0.22
     resistance
    0.22
    fight
    0.20
    Fight
    0.19
     fighting
    0.19
     Resistance
    0.16
    Activations Density 0.029%

    No Known Activations