Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 91851
    Prev
    Next
    INDEX
    Explanations

    Dashes/hyphens

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any tokens—it remains inactive and effectively matches nothing.

    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
    (buffer
    -0.08
     Kürt
    -0.07
    _flight
    -0.07
     Dal
    -0.07
    	from
    -0.07
    _busy
    -0.06
    ANDING
    -0.06
     Kata
    -0.06
     recipe
    -0.06
     July
    -0.06
    POSITIVE LOGITS
     Anglic
    0.06
     carniv
    0.06
     chắc
    0.06
    RSpec
    0.06
    Selector
    0.06
    .GeneratedValue
    0.06
     Formatting
    0.06
     beet
    0.06
    upro
    0.06
     Yosh
    0.06
    Activations Density 0.012%

    No Known Activations