© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90616
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    conversations involving ethical dilemmas and moral considerations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on the model’s self-descriptions about appearing or being “human” (e.g. phrases like “to appear more human than…”).

    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
     Ru
    -0.07
     pravděpodob
    -0.07
     rew
    -0.07
    (async
    -0.06
    ْر
    -0.06
     kết
    -0.06
    STRUCT
    -0.06
     scroll
    -0.06
     jumped
    -0.06
    imb
    -0.06
    POSITIVE LOGITS
    __,__
    0.07
    .rest
    0.06
     suit
    0.06
     bele
    0.06
     resta
    0.06
    ,target
    0.06
     sake
    0.06
    uffled
    0.06
    dling
    0.06
     nabí
    0.06
    Activations Density 0.032%

    No Known Activations