Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 122690
    Prev
    Next
    INDEX
    Explanations

    phone call transcripts

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _GU
    -0.07
     벌
    -0.06
     pořád
    -0.06
     рассчит
    -0.06
    otech
    -0.06
     سیاست
    -0.06
    351
    -0.06
     должен
    -0.06
     Pocket
    -0.06
    IBAction
    -0.06
    POSITIVE LOGITS
    	plt
    0.07
    ->[
    0.06
    (elm
    0.06
    acf
    0.06
     tearing
    0.06
    ージ
    0.06
    Thought
    0.06
    .chrome
    0.06
     Resident
    0.06
    Orig
    0.06
    Activations Density 0.018%

    No Known Activations