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. 23998
    Prev
    Next
    INDEX
    Explanations

    they

    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
    	timeout
    -0.07
    Bitcoin
    -0.07
    942
    -0.06
     organizations
    -0.06
     '"+
    -0.06
    91
    -0.06
    										↵
    -0.06
     →
    -0.06
     winds
    -0.06
    445
    -0.06
    POSITIVE LOGITS
    วก
    0.07
    νονται
    0.07
    (DWORD
    0.06
    στή
    0.06
    .showMessageDialog
    0.06
    (Level
    0.06
     трансп
    0.06
    ANTED
    0.06
    ичного
    0.06
     Erk
    0.06
    Activations Density 0.060%

    No Known Activations