© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33626
    Prev
    Next
    INDEX
    Explanations

    will be

    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
    -bound
    -0.07
     ÑįÑĦÑĦек
    -0.07
    âĢ¦)
    -0.07
    arrant
    -0.07
     disproportionately
    -0.07
     oci
    -0.07
    ÂŃs
    -0.07
    isOk
    -0.07
     QT
    -0.07
    ocket
    -0.06
    POSITIVE LOGITS
    ÂĢÂĢ
    0.12
    ******č\n
    0.11
     strSql
    0.11
    .synthetic
    0.10
    ¶Į
    0.10
    EMPLARY
    0.10
    ķãĤĵ
    0.10
    -------------</
    0.09
    ³ç´°
    0.09
    įng
    0.09
    Activations Density 0.008%

    No Known Activations