© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30696
    Prev
    Next
    INDEX
    Explanations

    instructions and possibilities

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs and modal verbs that introduce or structure procedural instructions (e.g. “check,” “request,” “attend,” “you can,” “submit,” “wait”).

    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
     handled
    -0.07
    �i
    -0.06
     graphs
    -0.06
     backups
    -0.06
    sat
    -0.06
    ев
    -0.06
    典
    -0.06
     interpretation
    -0.06
    	rep
    -0.06
     layout
    -0.06
    POSITIVE LOGITS
     yola
    0.07
    dcc
    0.06
     얘
    0.06
    乂
    0.06
     güven
    0.06
    ','','
    0.06
    -->
↵
    0.06
     jadx
    0.06
     erotische
    0.06
     '''
↵
    0.06
    Activations Density 0.028%

    No Known Activations