© 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. 13393
    Prev
    Next
    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash

    The neuron responds to words and phrases expressing romantic affection or emotional declarations (e.g., heart, loves, confess).

    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
     mere
    -0.06
    customerId
    -0.06
     simil
    -0.06
    ("");↵↵
    -0.06
    <meta
    -0.06
     divisive
    -0.06
    '])->
    -0.06
    퇴
    -0.06
     }];↵
    -0.06
    '];↵
    -0.06
    POSITIVE LOGITS
    _GR
    0.07
     predecess
    0.06
     Assumes
    0.06
    شن
    0.06
    (iOS
    0.06
    .tif
    0.06
     Oswald
    0.06
     】
    0.06
    /community
    0.06
    640
    0.06
    Activations Density 0.005%

    No Known Activations