© 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. 68865
    Prev
    Next
    INDEX
    Explanations

    commitment

    np_max-act · gemini-2.0-flash

    This neuron detects words related to making or specifying a contractual commitment (e.g., commit, commitment, contract length).

    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
     baiser
    -0.06
     Sağ
    -0.06
    .RESET
    -0.06
    って
    -0.06
     precios
    -0.06
    .reload
    -0.06
     kèm
    -0.06
     veces
    -0.06
     einf
    -0.06
     gracias
    -0.06
    POSITIVE LOGITS
     commitments
    0.08
    rn
    0.07
    =time
    0.07
    VN
    0.07
     lw
    0.06
     max
    0.06
     �
    0.06
     warranties
    0.06
     WB
    0.06
     PH
    0.06
    Activations Density 0.011%

    No Known Activations