© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 80817
    Prev
    Next
    INDEX
    Explanations

    name

    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
    odied
    -0.07
     Already
    -0.06
    ollapsed
    -0.06
     serial
    -0.06
     INTERRU
    -0.06
    orting
    -0.06
    caled
    -0.06
    xxxx
    -0.06
    acción
    -0.06
    inář
    -0.06
    POSITIVE LOGITS
    Won
    0.07
    .metadata
    0.07
     StringType
    0.07
     modelName
    0.06
    klass
    0.06
    	g
    0.06
     mName
    0.06
     synchronize
    0.06
    <bool
    0.06
     currentNode
    0.06
    Activations Density 0.001%

    No Known Activations