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. 15-RESID-POST-AA
    6. 122963
    Prev
    Next
    INDEX
    Explanations

    :

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Omega
    -0.06
     Για
    -0.06
    	log
    -0.06
     пан
    -0.06
    lte
    -0.06
     Cros
    -0.06
     �
    -0.06
    DetailsService
    -0.06
    	UP
    -0.06
     kidn
    -0.06
    POSITIVE LOGITS
     negatively
    0.07
     Ancient
    0.06
    fa
    0.06
    quia
    0.06
     wardrobe
    0.06
     Samoa
    0.06
     Quebec
    0.06
    _jump
    0.06
    fruit
    0.06
     Savings
    0.06
    Activations Density 0.003%

    No Known Activations