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. 65148
    Prev
    Next
    INDEX
    Explanations

    not based or not tested

    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
    borg
    -0.10
    achat
    -0.09
    uluk
    -0.09
    raya
    -0.09
     lore
    -0.09
     theorists
    -0.09
    å°ijå¹´
    -0.09
    uben
    -0.09
    JSONException
    -0.09
    ivent
    -0.09
    POSITIVE LOGITS
     test
    0.13
     burden
    0.13
     fals
    0.13
    emp
    0.12
     Emp
    0.11
     proof
    0.11
    -proof
    0.11
     claims
    0.11
     realm
    0.10
     Test
    0.10
    Activations Density 0.067%

    No Known Activations