© 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. 4373
    Prev
    Next
    INDEX
    Explanations

    familiar / recognizable

    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
    strap
    -0.09
    subst
    -0.08
     realizing
    -0.08
    :.:
    -0.08
     Katz
    -0.08
    ulfill
    -0.08
    alborg
    -0.08
    èĢĥãģĪ
    -0.08
    _nat
    -0.08
    alon
    -0.08
    POSITIVE LOGITS
     familiar
    0.86
     Fam
    0.66
    çĨŁ
    0.63
     familiarity
    0.62
    amiliar
    0.56
     fam
    0.46
    recogn
    0.42
     recogn
    0.42
     recognizable
    0.39
     recognize
    0.38
    Activations Density 0.238%

    No Known Activations