© 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
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 102591
    Prev
    Next
    INDEX
    Explanations

    Partnership events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    been
    -0.07
     IDictionary
    -0.07
     DAT
    -0.07
     рук
    -0.07
     revelations
    -0.07
    J
    -0.07
    webdriver
    -0.06
    (nonatomic
    -0.06
     envy
    -0.06
    OME
    -0.06
    POSITIVE LOGITS
     lip
    0.07
     Naruto
    0.06
    lamaya
    0.06
    _WAIT
    0.06
     сделать
    0.06
     practicing
    0.06
    moth
    0.06
    iyoruz
    0.06
    pez
    0.06
    izzlies
    0.05
    Activations Density 0.052%

    No Known Activations