© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9027
    Prev
    Next
    INDEX
    Explanations

    Hallucination/embellishment

    np_max-act · gemini-2.0-flash

    legislative terms and concepts related to healthcare policy.

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

    The neuron fires on occurrences of the word “hallucinate.”

    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
     ヽ
    -0.08
     ForeignKey
    -0.08
     farewell
    -0.07
    cete
    -0.07
     CancellationToken
    -0.07
     disappe
    -0.06
     �
    -0.06
    _datasets
    -0.06
     восп
    -0.06
    .age
    -0.06
    POSITIVE LOGITS
     abilities
    0.07
     marvelous
    0.06
    CAPE
    0.06
    今日
    0.06
    Hibernate
    0.06
    .Hit
    0.06
     DC
    0.06
     TOM
    0.06
    وقف
    0.06
     repell
    0.06
    Activations Density 0.000%

    No Known Activations