© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 38634
    Prev
    Next
    INDEX
    Explanations

    expressing willingness to help or know

    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
     zur
    -0.12
    what
    -0.09
    the
    -0.09
     dazu
    -0.09
    ral
    -0.09
    dat
    -0.09
    rale
    -0.09
    932
    -0.09
    isse
    -0.09
    igen
    -0.09
    POSITIVE LOGITS
     assistance
    0.24
     help
    0.23
     Assistance
    0.19
     talk
    0.16
     me
    0.13
     Hilfe
    0.13
     ayuda
    0.13
     discuss
    0.12
     follando
    0.12
     Help
    0.12
    Activations Density 0.018%

    No Known Activations