© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 97513
    Prev
    Next
    INDEX
    Explanations

    single

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scream
    -0.07
     úspě
    -0.07
     ----------↵
    -0.07
     όμως
    -0.07
     remarked
    -0.06
    	alpha
    -0.06
     jeu
    -0.06
     na
    -0.06
    Upload
    -0.06
     down
    -0.06
    POSITIVE LOGITS
     المق
    0.07
     **)&
    0.06
     preceding
    0.06
     LSD
    0.06
    floating
    0.06
    ritis
    0.06
     franchise
    0.06
    enght
    0.06
     inner
    0.06
    quired
    0.06
    Activations Density 0.007%

    No Known Activations