© 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. 871
    Prev
    Next
    INDEX
    Explanations

    Israeli occupation of West Bank

    np_max-act · gemini-2.0-flash

    The neuron activates on terms referring to the Israeli–Palestinian territorial occupation (e.g. occupation, occupied, settlements, West Bank, Gaza).

    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
    lda
    -0.07
    verbosity
    -0.07
    _collect
    -0.06
    بير
    -0.06
    .ie
    -0.06
    _creator
    -0.06
     squirrel
    -0.06
     EVERY
    -0.06
    _HAVE
    -0.06
     yesterday
    -0.06
    POSITIVE LOGITS
     guidance
    0.07
     ''↵↵
    0.06
     Guidance
    0.06
    WIN
    0.06
     През
    0.06
    genome
    0.06
     unpredict
    0.06
     ordin
    0.06
     фор
    0.06
     Terrorism
    0.06
    Activations Density 0.004%

    No Known Activations