© 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. 55867
    Prev
    Next
    INDEX
    Explanations

    ¡

    np_max-act · gemini-2.0-flash

    The neuron detects the Spanish opening exclamation mark “¡.”

    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
     gw
    -0.07
     }])↵
    -0.07
     soğ
    -0.06
     convers
    -0.06
    通过
    -0.06
    _ag
    -0.06
     �
    -0.06
     Eff
    -0.06
     сп
    -0.06
     nestled
    -0.06
    POSITIVE LOGITS
    mil
    0.06
    -user
    0.06
     Atomic
    0.06
     Mellon
    0.06
    xy
    0.06
     nation
    0.06
    Attempts
    0.06
    meric
    0.06
     Electronics
    0.06
     Cannot
    0.06
    Activations Density 0.004%

    No Known Activations