© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125981
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on past‐tense verb forms (especially auxiliaries like “was” and “were”) in narrative passages.

    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
    Disney
    -0.06
     musician
    -0.06
    atitis
    -0.06
    Hall
    -0.06
     Travel
    -0.06
     sơn
    -0.06
     initiatives
    -0.06
    .ne
    -0.06
    国产
    -0.06
     Florian
    -0.06
    POSITIVE LOGITS
    _DECLARE
    0.07
     Recursive
    0.07
     divide
    0.07
    .....↵↵
    0.07
    PING
    0.06
      ↵
    0.06
    .unregister
    0.06
    (':',
    0.06
     embarrassing
    0.06
    EXIT
    0.06
    Activations Density 0.053%

    No Known Activations