© 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. 34591
    Prev
    Next
    INDEX
    Explanations

    tamper

    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
    AppName
    -0.10
    nech
    -0.10
    entr
    -0.09
     Twilight
    -0.09
    bian
    -0.09
    egov
    -0.09
    mma
    -0.09
    ipp
    -0.09
    mium
    -0.09
    entes
    -0.09
    POSITIVE LOGITS
    Tam
    0.17
     tam
    0.17
     Tam
    0.15
    quam
    0.15
    pering
    0.14
    tam
    0.13
     TAM
    0.13
    pered
    0.13
    รวà¸Ī
    0.13
    adge
    0.11
    Activations Density 0.026%

    No Known Activations