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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 18358
    Prev
    Next
    INDEX
    Explanations

    Halloween

    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_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
     Müller
    -0.08
     orbital
    -0.07
     bure
    -0.07
     ISR
    -0.06
     sunt
    -0.06
    Ст
    -0.06
    YRO
    -0.06
    itunes
    -0.06
     meth
    -0.06
     mü
    -0.06
    POSITIVE LOGITS
     Halloween
    0.13
    alloween
    0.08
    なん
    0.07
    황
    0.07
     spooky
    0.06
     los
    0.06
     인
    0.06
     drained
    0.06
     flavored
    0.06
     vài
    0.06
    Activations Density 0.003%

    No Known Activations