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. 19-RESID-POST-AA
    6. 9851
    Prev
    Next
    INDEX
    Explanations

    "known"

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     borr
    -0.07
     sequences
    -0.06
     ا
    -0.06
     lb
    -0.06
    Reward
    -0.06
    	f
    -0.06
     �
    -0.06
    回答
    -0.06
    导
    -0.06
    něji
    -0.06
    POSITIVE LOGITS
    である
    0.06
     enhanced
    0.06
    (cart
    0.06
    calc
    0.06
     logic
    0.06
     Byz
    0.06
     knows
    0.06
     magical
    0.06
     asoci
    0.06
     anarch
    0.06
    Activations Density 0.014%

    No Known Activations