© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43667
    Prev
    Next
    INDEX
    Explanations

    familiar and stable

    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
     Riy
    -0.09
     Brotherhood
    -0.09
    ":"'
    -0.08
     freshness
    -0.08
    æĥł
    -0.08
     tÆ°Æ¡i
    -0.08
     RAT
    -0.08
    ç³
    -0.08
     starter
    -0.08
     stair
    -0.08
    POSITIVE LOGITS
     familiar
    0.51
     Fam
    0.43
     familiarity
    0.39
    çĨŁ
    0.38
    amiliar
    0.37
     fam
    0.27
     routine
    0.26
     comfort
    0.25
     ìĿµ
    0.25
     predict
    0.24
    Activations Density 0.114%

    No Known Activations