© 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. 55520
    Prev
    Next
    INDEX
    Explanations

    right and wrong

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “wrong” (especially in the phrase “it’s wrong”) in the assistant’s evaluation responses.

    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
    ्वत
    -0.07
    _land
    -0.07
     عل
    -0.06
     investigators
    -0.06
     hy
    -0.06
    _hom
    -0.06
     detach
    -0.06
    ною
    -0.06
     úrov
    -0.06
     Meghan
    -0.06
    POSITIVE LOGITS
    igDecimal
    0.06
    打
    0.06
     Linda
    0.06
    381
    0.06
    ۹
    0.06
    incorrect
    0.06
    ewire
    0.06
     Biden
    0.06
     centerpiece
    0.06
    dent
    0.06
    Activations Density 0.002%

    No Known Activations