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. 34345
    Prev
    Next
    INDEX
    Explanations

    writing in a specific style

    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
    eload
    -0.10
     Tall
    -0.09
     contacts
    -0.09
    allback
    -0.08
     Perm
    -0.08
    OUCH
    -0.08
    æī¶
    -0.08
    uche
    -0.08
    kontakte
    -0.08
    isel
    -0.08
    POSITIVE LOGITS
     conversation
    0.13
     spoken
    0.12
     actual
    0.12
     journal
    0.11
     spoke
    0.10
     diary
    0.10
    actual
    0.10
     lazy
    0.10
    Lazy
    0.10
     drunken
    0.09
    Activations Density 0.179%

    No Known Activations