Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 34233
    Prev
    Next
    INDEX
    Explanations

    plan and action

    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
    gere
    -0.09
    ois
    -0.09
    ToBounds
    -0.09
    ment
    -0.09
    uite
    -0.09
     Wolff
    -0.09
     Walters
    -0.08
     slashing
    -0.08
    çī
    -0.08
    igure
    -0.08
    POSITIVE LOGITS
     action
    0.18
     plan
    0.15
     Parenthood
    0.13
     paren
    0.13
    -action
    0.13
    ogram
    0.12
    огÑĢам
    0.12
    isphere
    0.12
    -plan
    0.12
    alto
    0.12
    Activations Density 0.034%

    No Known Activations