© 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. 34136
    Prev
    Next
    INDEX
    Explanations

    explain concept of

    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
    ÂĢÂĢ
    -0.09
    lardan
    -0.09
    Animating
    -0.09
    ONTAL
    -0.08
    įng
    -0.08
    -cigaret
    -0.08
     pÅĻedpis
    -0.08
     cmdline
    -0.08
    uba
    -0.08
    ifes
    -0.08
    POSITIVE LOGITS
     cookies
    0.10
     Cookies
    0.09
     meant
    0.09
    Âł
    0.09
    laus
    0.09
     pare
    0.09
    -types
    0.09
     sunk
    0.09
     Terms
    0.09
     lag
    0.09
    Activations Density 0.288%

    No Known Activations