© 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. 29999
    Prev
    Next
    INDEX
    Explanations

    possessives

    np_max-act · gemini-2.0-flash

    The neuron activates on possessive references, i.e. tokens marking ownership such as “her,” “his,” or a character’s name with ’s.

    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
    vt
    -0.07
    .failure
    -0.06
     teas
    -0.06
    skému
    -0.06
    �
    -0.06
    getList
    -0.06
     easier
    -0.06
    Want
    -0.06
     якому
    -0.06
     bpm
    -0.06
    POSITIVE LOGITS
     cush
    0.07
     давно
    0.07
     recycle
    0.06
     deter
    0.06
    汽
    0.06
     ضد
    0.06
     校
    0.06
    ัตว
    0.06
    owane
    0.06
    erialized
    0.06
    Activations Density 0.037%

    No Known Activations