© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44954
    Prev
    Next
    INDEX
    Explanations

    went

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the past‐tense verb “went.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ro
    -0.07
     BAB
    -0.07
    _ro
    -0.07
    Hora
    -0.06
    ตลาด
    -0.06
    dro
    -0.06
     dří
    -0.06
    -cor
    -0.06
     dor
    -0.06
     продаж
    -0.06
    POSITIVE LOGITS
     went
    0.16
     Went
    0.10
    went
    0.10
     goes
    0.09
     going
    0.09
     came
    0.08
    nEnter
    0.08
    くと
    0.08
    .End
    0.08
     end
    0.08
    Activations Density 0.010%

    No Known Activations