© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95256
    Prev
    Next
    INDEX
    Explanations

    opinion

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROPERTY
    -0.07
     thuật
    -0.07
    课
    -0.07
     HOLDER
    -0.06
    006
    -0.06
    Weekly
    -0.06
     Clemson
    -0.06
    學校
    -0.06
    RESET
    -0.06
    002
    -0.06
    POSITIVE LOGITS
     opinion
    0.08
     bev
    0.06
    iny
    0.06
    ements
    0.06
    .Mail
    0.06
     opin
    0.06
    рой
    0.06
     Tone
    0.06
     tilt
    0.06
    	email
    0.06
    Activations Density 0.016%

    No Known Activations