© 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. 34111
    Prev
    Next
    INDEX
    Explanations

    IAM roles and access management

    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
     Authenticate
    -0.09
     VL
    -0.09
     Mun
    -0.09
    ades
    -0.09
     Vlad
    -0.09
    LLU
    -0.09
    oric
    -0.08
    zing
    -0.08
    raq
    -0.08
     Administration
    -0.08
    POSITIVE LOGITS
    iam
    0.18
     role
    0.18
     assume
    0.17
    _ASSUME
    0.16
     Role
    0.16
    arn
    0.15
     assum
    0.14
    -role
    0.14
     assumed
    0.14
     Arn
    0.14
    Activations Density 0.039%

    No Known Activations