© 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. 34673
    Prev
    Next
    INDEX
    Explanations

    presence or absence of items

    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
    _MODIFIED
    -0.08
    afi
    -0.08
    enty
    -0.08
     огÑĢа
    -0.08
    âĹıâĹı
    -0.08
     åŁº
    -0.08
    (Target
    -0.07
    åŁºäºİ
    -0.07
    unkt
    -0.07
    .getFullYear
    -0.07
    POSITIVE LOGITS
     presence
    0.13
    presence
    0.10
     Presence
    0.10
     optional
    0.10
     added
    0.09
     налиÑĩие
    0.09
    Presence
    0.09
     missing
    0.09
    ogg
    0.08
    éĤ£ä¸ª
    0.08
    Activations Density 0.151%

    No Known Activations