© 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. 30480
    Prev
    Next
    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens expressing refusal or inability (e.g. “can’t,” “refuse,” “sorry”).

    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
    ользов
    -0.07
     container
    -0.07
    �
    -0.06
    試
    -0.06
    Mit
    -0.06
     Brave
    -0.06
    (sec
    -0.06
     move
    -0.06
     containers
    -0.06
     tests
    -0.06
    POSITIVE LOGITS
     inherently
    0.08
     innovate
    0.07
     marginalized
    0.06
     Herman
    0.06
     جنوبی
    0.06
     SignUp
    0.06
    STRACT
    0.06
    ickém
    0.06
     pylab
    0.06
     外部リンク
    0.06
    Activations Density 0.008%

    No Known Activations