© 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. 110560
    Prev
    Next
    INDEX
    Explanations

    person

    np_max-act · gemini-2.0-flash

    legal terminologies and phrases related to court proceedings and rulings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on phrasing invoking the “reasonable person” standard (e.g. “reasonable person … would …”).

    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
     FD
    -0.08
    ❤
    -0.07
    ngoing
    -0.06
    овж
    -0.06
    Misc
    -0.06
    Arrange
    -0.06
    손
    -0.06
     wäh
    -0.06
     fayd
    -0.06
     Hra
    -0.06
    POSITIVE LOGITS
     compress
    0.06
    _InitStruct
    0.06
    _LIB
    0.06
    	cb
    0.06
     Insp
    0.06
    (adapter
    0.06
     ideally
    0.06
     Or
    0.06
    _COMPAT
    0.06
    pcf
    0.06
    Activations Density 0.002%

    No Known Activations