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. 93188
    Prev
    Next
    INDEX
    Explanations

    We

    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
    iller
    -0.07
     đ�
    -0.06
    +'
    -0.06
     řed
    -0.06
    уля
    -0.06
    PROFILE
    -0.06
    还有
    -0.06
    ')]
    -0.06
    imat
    -0.06
    zenie
    -0.06
    POSITIVE LOGITS
     My
    0.07
     indice
    0.07
    _DX
    0.07
     closet
    0.07
    	Double
    0.07
     costo
    0.07
    (non
    0.07
     I
    0.07
     thanking
    0.06
    Observ
    0.06
    Activations Density 0.011%

    No Known Activations