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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44956
    Prev
    Next
    INDEX
    Explanations

    words starting with ale

    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
     Rarity
    -0.10
    tul
    -0.10
    acker
    -0.09
    d
    -0.09
    ppers
    -0.09
     Legend
    -0.09
    alter
    -0.09
    acle
    -0.09
    erve
    -0.09
    uegos
    -0.08
    POSITIVE LOGITS
    poÅĪ
    0.14
    jandro
    0.14
    ardy
    0.12
    atoire
    0.12
    andro
    0.12
    Ìģ
    0.11
    wives
    0.11
    wife
    0.11
    mpi
    0.11
    ENU
    0.11
    Activations Density 0.026%

    No Known Activations