© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 42687
    Prev
    Next
    INDEX
    Explanations

    finances

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases about obtaining money or financing (actions like selling, taking, issuing stock, dealing, or otherwise sourcing funds).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    491
    -0.07
     khí
    -0.06
    837
    -0.06
    Cities
    -0.06
    419
    -0.06
     provoked
    -0.06
     Selection
    -0.06
     Instrument
    -0.06
     precipitation
    -0.06
    817
    -0.06
    POSITIVE LOGITS
    олай
    0.06
    atype
    0.06
     personne
    0.06
     sürekli
    0.06
    .dat
    0.06
    -shadow
    0.06
     DM
    0.06
     starší
    0.06
    (span
    0.06
     becer
    0.06
    Activations Density 0.233%

    No Known Activations