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. 7-RESID-POST-AA
    6. 128814
    Prev
    Next
    INDEX
    Explanations

    )

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deutschland
    -0.06
    /book
    -0.06
     pov
    -0.06
     작은
    -0.06
    GBT
    -0.06
    е�
    -0.06
     DWC
    -0.06
    (bean
    -0.06
     rabbits
    -0.06
    _shutdown
    -0.06
    POSITIVE LOGITS
    	Document
    0.07
    primir
    0.07
     realized
    0.06
    CompatActivity
    0.06
    unday
    0.06
    	final
    0.06
     První
    0.06
    ='+
    0.06
    =[]↵
    0.06
    ++){↵
    0.06
    Activations Density 0.020%

    No Known Activations