© 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. 44391
    Prev
    Next
    INDEX
    Explanations

    manipulation, exploitation, accumulation, manicure

    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
    er
    -0.11
     Eaton
    -0.11
    gency
    -0.10
    GD
    -0.10
    ings
    -0.10
     chir
    -0.10
    able
    -0.10
    t
    -0.10
    na
    -0.09
    ified
    -0.09
    POSITIVE LOGITS
    ulative
    0.18
    ulations
    0.16
    ulation
    0.14
    ulating
    0.11
    ulated
    0.11
    ulação
    0.11
    actionDate
    0.11
    hest
    0.11
    ulators
    0.10
     Manip
    0.10
    Activations Density 0.028%

    No Known Activations