© 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
    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. 44388
    Prev
    Next
    INDEX
    Explanations

    slang

    np_max-act · gemini-2.0-flash

    The neuron fires on “meta” style‐directive words describing a chatty tone (e.g. modern, American, slang, emojis), i.e. instructions about using modern American slang and emojis.

    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
    ималь
    -0.08
    .creation
    -0.07
    ροι
    -0.07
    .Dto
    -0.07
     Pin
    -0.06
     Amp
    -0.06
     link
    -0.06
     Cardio
    -0.06
    れている
    -0.06
    Pin
    -0.06
    POSITIVE LOGITS
     SUCH
    0.07
     troub
    0.07
     rearr
    0.06
     ranking
    0.06
    ucz
    0.06
     teachers
    0.06
     repertoire
    0.06
    venge
    0.06
     cb
    0.05
    ाँ
    0.05
    Activations Density 0.010%

    No Known Activations