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. 27-RESID-POST-AA
    6. 72993
    Prev
    Next
    INDEX
    Explanations

    demonstrate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     специалист
    -0.07
     respond
    -0.06
    ITU
    -0.06
    >").
    -0.06
    _WRITE
    -0.06
     програм
    -0.06
    quake
    -0.06
    ]),
    -0.06
     participated
    -0.06
     sermon
    -0.06
    POSITIVE LOGITS
    -secret
    0.06
    dog
    0.06
     aff
    0.06
    ραβ
    0.06
     hallmark
    0.06
    _bound
    0.06
    ใ
    0.06
    _Val
    0.06
     zest
    0.06
    _bb
    0.06
    Activations Density 0.046%

    No Known Activations