© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 103692
    Prev
    Next
    INDEX
    Explanations

    his

    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
     we
    -0.08
     seleccion
    -0.07
     CREATE
    -0.07
    	byte
    -0.07
     We
    -0.07
    /e
    -0.06
     плен
    -0.06
    ับค
    -0.06
     automobile
    -0.06
     According
    -0.06
    POSITIVE LOGITS
     his
    0.11
    His
    0.11
     His
    0.10
     HIS
    0.09
     her
    0.08
     अस
    0.07
    ihil
    0.07
    his
    0.07
    hist
    0.07
     HER
    0.07
    Activations Density 0.056%

    No Known Activations