Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 124877
    Prev
    Next
    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —but
    -0.07
    PRICE
    -0.06
    —if
    -0.06
     observable
    -0.06
    žít
    -0.06
    (get
    -0.06
    ecal
    -0.06
    YK
    -0.06
    PERTY
    -0.06
     yapar
    -0.06
    POSITIVE LOGITS
    DevExpress
    0.07
    _phy
    0.07
     หล
    0.07
    ざ
    0.07
     nightclub
    0.06
    „ظ
    0.06
    ยวข
    0.06
     νεφοκάλυψης
    0.06
     самост
    0.06
     심
    0.06
    Activations Density 0.004%

    No Known Activations