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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-RESID-POST-AA
    6. 103937
    Prev
    Next
    INDEX
    Explanations

    Bulgaria

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     случаях
    -0.07
     shl
    -0.07
    import
    -0.06
    >()
    -0.06
     �
    -0.06
    }',
    -0.06
    puties
    -0.06
    `).
    -0.06
    حداث
    -0.06
     جد
    -0.06
    POSITIVE LOGITS
    atis
    0.08
     starch
    0.06
     stagger
    0.06
                
    0.06
     автомати
    0.06
     merry
    0.06
    _fore
    0.06
     meis
    0.06
    þ
    0.06
     člov
    0.05
    Activations Density 0.035%

    No Known Activations