© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 72173
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to fragments of anime titles and metadata (e.g. subword pieces of show names, “anime,” “Episode,” “Blu-ray,” etc.), effectively flagging where an anime series or episode is being referenced.

    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
    _eng
    -0.07
     군
    -0.06
     obtain
    -0.06
     buff
    -0.06
    基
    -0.06
    -img
    -0.06
     describes
    -0.06
    	ERR
    -0.06
     各
    -0.06
     코
    -0.06
    POSITIVE LOGITS
    Namespace
    0.07
     Clock
    0.07
    -placeholder
    0.07
     asiat
    0.06
     Phật
    0.06
     signalling
    0.06
    %)↵
    0.06
    identifier
    0.06
    itation
    0.06
     Session
    0.06
    Activations Density 0.031%

    No Known Activations