© 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. 125209
    Prev
    Next
    INDEX
    Explanations

    deliver

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on the word “deliver” (and its close variants) in the text.

    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
     bothering
    -0.07
     Sheep
    -0.07
     considered
    -0.07
    _idx
    -0.07
     facto
    -0.06
     NOTE
    -0.06
     grown
    -0.06
     Study
    -0.06
     SPD
    -0.06
     studied
    -0.06
    POSITIVE LOGITS
     deliver
    0.12
     delivered
    0.11
     delivering
    0.10
     Deliver
    0.10
     delivers
    0.10
    �
    0.07
    loser
    0.07
     lái
    0.07
    deliver
    0.07
    全面
    0.07
    Activations Density 0.013%

    No Known Activations