© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 112325
    Prev
    Next
    INDEX
    Explanations

    learning

    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
    .psi
    -0.07
    Pix
    -0.07
     traf
    -0.07
     salads
    -0.06
     форма
    -0.06
     бед
    -0.06
     Sistem
    -0.06
     sidew
    -0.06
     coat
    -0.06
     mpz
    -0.06
    POSITIVE LOGITS
     learning
    0.08
     Learning
    0.07
    لب
    0.07
    ollower
    0.07
     bound
    0.07
    тя
    0.07
    lider
    0.06
    lý
    0.06
     "==
    0.06
     surrounding
    0.06
    Activations Density 0.013%

    No Known Activations