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. 19-RESID-POST-AA
    6. 83675
    Prev
    Next
    INDEX
    Explanations

    text adventure choices

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يد
    -0.07
     사람은
    -0.06
              
    ↵
    -0.06
    @a
    -0.06
    MaxLength
    -0.06
    contentType
    -0.06
    .del
    -0.06
     }));↵↵
    -0.06
     Modifications
    -0.06
     ]);
    -0.06
    POSITIVE LOGITS
     esse
    0.07
    391
    0.07
    (笑
    0.07
    ̧
    0.06
     northeastern
    0.06
    prehensive
    0.06
     موفق
    0.06
    izyon
    0.06
    ’hui
    0.06
     odpowied
    0.06
    Activations Density 0.017%

    No Known Activations