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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 46788
    Prev
    Next
    INDEX
    Explanations

    entity that"}, "entity types"}, "entity names"}, "entity type"}, "entity keys"}, "entity that"}

    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
    obe
    -0.10
    ÑĦек
    -0.10
    lect
    -0.10
    anne
    -0.10
    /errors
    -0.09
    atr
    -0.09
    bill
    -0.09
    ison
    -0.09
    lec
    -0.09
    lee
    -0.09
    POSITIVE LOGITS
    ties
    0.13
    (Entity
    0.12
    yyyy
    0.12
    .Entity
    0.11
    .ResponseEntity
    0.11
    osph
    0.10
    alink
    0.10
    ies
    0.10
    prising
    0.09
    _QUOTES
    0.09
    Activations Density 0.041%

    No Known Activations