© 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. 9445
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific place or organization names (e.g. cities, states, or news outlets).

    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
    换
    -0.07
    发布
    -0.07
     پیشنه
    -0.06
    504
    -0.06
     cluster
    -0.06
    .windows
    -0.06
     launch
    -0.06
    /mp
    -0.06
    cue
    -0.06
    .ico
    -0.06
    POSITIVE LOGITS
    告
    0.06
     battered
    0.06
    RecognitionException
    0.06
     setContent
    0.06
     учит
    0.06
     yo
    0.06
    hoo
    0.06
    _Value
    0.06
     đèn
    0.06
     Nobel
    0.06
    Activations Density 0.049%

    No Known Activations