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. 15-RESID-POST-AA
    6. 60101
    Prev
    Next
    INDEX
    Explanations

    slight improvement

    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
    كت
    -0.06
     workspace
    -0.06
     EMS
    -0.06
     fruits
    -0.06
     imageName
    -0.06
     rover
    -0.06
    -module
    -0.06
    loadModel
    -0.06
     percentile
    -0.06
     governors
    -0.06
    POSITIVE LOGITS
     Erin
    0.06
     KING
    0.06
     �
    0.06
    =batch
    0.06
    methods
    0.06
     Wh
    0.06
     discovers
    0.06
     unlocks
    0.06
    	elif
    0.06
    دا
    0.06
    Activations Density 0.058%

    No Known Activations