© 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. 110195
    Prev
    Next
    INDEX
    Explanations

    Business/technical contexts

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the multi‐word legal/contractual phrase “intellectual property right holder.”

    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
     sempre
    -0.07
    Boss
    -0.07
    .nd
    -0.06
    .next
    -0.06
     Agenda
    -0.06
    picable
    -0.06
    Products
    -0.06
    .record
    -0.06
    Earlier
    -0.06
    Def
    -0.06
    POSITIVE LOGITS
    リンク
    0.07
    mbH
    0.07
    .MOD
    0.07
     tumult
    0.06
    orses
    0.06
    _Link
    0.06
    ับการ
    0.06
    ROME
    0.06
     explore
    0.06
    rate
    0.06
    Activations Density 0.053%

    No Known Activations