© 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. 34690
    Prev
    Next
    INDEX
    Explanations

    explaining fundamental observations

    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
    opp
    -0.10
    428
    -0.09
    머ëĭĪ
    -0.09
     Doming
    -0.09
    prit
    -0.09
     ç¿
    -0.08
     direct
    -0.08
    orie
    -0.08
    ARGS
    -0.08
    enga
    -0.08
    POSITIVE LOGITS
     observed
    0.29
     observations
    0.22
     phenomena
    0.21
    obs
    0.17
    observations
    0.17
     phenomenon
    0.17
     why
    0.16
     наблÑİд
    0.16
    _obs
    0.16
     apparent
    0.15
    Activations Density 0.069%

    No Known Activations