© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44494
    Prev
    Next
    INDEX
    Explanations

    absence or missing information

    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
    unlikely
    -0.12
     Unsure
    -0.11
    opro
    -0.10
     unlikely
    -0.10
    activex
    -0.09
     thừa
    -0.09
    afari
    -0.08
     WITHOUT
    -0.08
     WRONG
    -0.08
    Impossible
    -0.08
    POSITIVE LOGITS
     absent
    0.34
     missing
    0.32
    missing
    0.26
     absence
    0.25
     wasn
    0.25
     Missing
    0.24
    Missing
    0.22
     nowhere
    0.22
    _missing
    0.22
     оÑĤÑģÑĥÑĤÑģÑĤв
    0.21
    Activations Density 0.167%

    No Known Activations