© 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. 34063
    Prev
    Next
    INDEX
    Explanations

    common ancestor

    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
     sons
    -0.13
     Sons
    -0.12
     Daughter
    -0.11
     grandson
    -0.11
     Neighbor
    -0.11
     Born
    -0.11
     hijo
    -0.10
     hijos
    -0.10
     nephew
    -0.10
     heirs
    -0.10
    POSITIVE LOGITS
     ancestor
    0.40
     ancestors
    0.39
     predecessor
    0.36
     predecessors
    0.33
    ancestor
    0.32
    decess
    0.32
    ç¥ĸ
    0.32
     predecess
    0.31
     fore
    0.27
     pÅĻedch
    0.27
    Activations Density 0.155%

    No Known Activations